Transaction processing method and device

Abstract

The embodiments of the present specification provide a transaction processing method and device, wherein the transaction processing method includes: receiving a termination instruction initiated by a user for a transaction order, the termination instruction including operation information input by the user, predicting the user's termination intention information based on the operation information, and determining to display an order operation interface with recommended information to the user based on the termination intention information, so that the user can process the termination operation of the transaction order according to the order operation interface.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and more particularly to transaction processing methods and devices. Background Art

[0002] With the rapid development of Internet technology, shopping through Internet platforms is becoming more and more common, and Internet platforms make users' commodity purchases more convenient and diverse, and more and more users are beginning to rely on Internet consumption platforms for consumption. At the same time, with the rapid development of mobile payment technology and the continuous upgrading of mobile terminals (such as smart phones), using mobile terminals to complete offline payments has become an indispensable part of people's daily lives.

[0003] However, in the commodity transaction process, after the buyer pays the consumption amount to the Internet platform, a refund may be required due to various reasons. Usually, for the refund application initiated by the buyer, the seller's processing method is mainly: after receiving the refund request, determine the refund amount and refund path according to the refund request, and refund based on the refund path; after the buyer initiates the refund request, no effective measures are taken to provide products that are more in line with user needs or of higher quality, thereby reducing the time for users to re-search for the required products. Therefore, a transaction processing method is urgently needed to solve such problems. Summary of the invention

[0004] In view of this, the embodiments of this specification provide a transaction processing method. One or more embodiments of this specification also relate to an information recommendation method, a transaction processing device, an information recommendation device, a computing device, and a computer-readable storage medium to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a transaction processing method is provided, including:

[0006] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0007] Based on the operation information, predicting the user's termination intention information;

[0008] Based on the termination intention information, determine to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface.

[0009] Optionally, the determining, based on the termination intention information, to display an order operation interface carrying recommendation information to the user includes:

[0010] Determining the recommended information and the order processing path corresponding to the termination instruction according to the termination intention information;

[0011] An order operation interface carrying the recommendation information is displayed to the user according to the order processing path.

[0012] Optionally, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, the method further includes:

[0013] Receiving feedback information submitted by the user based on the order operation interface;

[0014] In the case where it is determined according to the feedback information that the user confirms to accept the recommendation information, it is determined that the recommendation information is triggered, and the termination instruction is cancelled.

[0015] Optionally, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, the method further includes:

[0016] If no feedback information submitted by the user for the recommendation information is received, executing the termination instruction; or,

[0017] receiving feedback information submitted by the user regarding the recommendation information;

[0018] In the case where it is determined according to the feedback information that the user refuses to accept the recommendation information, it is determined that the recommendation information is not triggered, and the termination instruction is executed.

[0019] Optionally, determining the recommended information and the order processing path corresponding to the termination instruction according to the termination intention information includes:

[0020] Acquire a matching relationship between the termination intention information and a processing method of the termination instruction;

[0021] Determining a target processing method that matches the termination intention information according to the matching relationship;

[0022] Determine a processing rule for at least one termination instruction in the target processing method whose probability of being triggered meets a preset probability threshold, and use the processing rule as the recommended information, and use the information sending method in which the probability of the recommended information being triggered is greater than the preset probability threshold as the order processing path.

[0023] Optionally, presenting an order operation interface carrying the recommendation information to the user according to the order processing path includes:

[0024] Performing interface rendering based on the recommendation information, generating an order operation interface and displaying it to the user; the order operation interface includes clickable controls;

[0025] Accordingly, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, the method further includes:

[0026] Detecting a click operation performed by the user on the order operation interface;

[0027] In the case where it is detected that the user submits a confirmation instruction by clicking the clickable control, the recommendation information is triggered and the termination instruction is cancelled; or

[0028] In the case where the user does not click on the clickable control, the termination instruction is executed.

[0029] Optionally, before the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is performed, the method further includes:

[0030] Query the historical display record of displaying the order operation interface to the user for the transaction order;

[0031] If the query result is empty, the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed.

[0032] Optionally, presenting an order operation interface carrying the recommendation information to the user according to the order processing path includes:

[0033] Determine a component template of a component to be displayed corresponding to the recommendation information;

[0034] The component template is rendered using the recommendation information as rendering data to generate an information display component, which is then displayed to the user through an information interaction window; the information interaction window includes clickable controls.

[0035] Optionally, the transaction processing method further includes:

[0036] Calling a conversation interface to interact with the user, and sending the recommendation information to the user by sending a voice message during the conversation;

[0037] Receiving voice information and / or key feedback information returned by the user during the conversation;

[0038] If it is determined according to the voice information and / or the key feedback information that the user confirms to accept the recommendation information, the recommendation information is triggered and the termination instruction is cancelled; or

[0039] If it is determined according to the voice information and / or the key feedback information that the user refuses to accept the recommendation information, the recommendation information is not triggered and the termination instruction is executed.

[0040] Optionally, before the step of calling the conversation interface to interact with the user in a conversation and sending the recommendation information to the user by sending a voice message during the conversation, the step further includes:

[0041] Determining a session interaction time for performing a session interaction with the user;

[0042] Determining whether the conversation interaction time falls within a preset time interval;

[0043] If so, query the interaction record of the conversation interaction with the user within a preset time period, and determine whether the interaction record is empty;

[0044] If the interaction record is empty, the step of calling the conversation interface to interact with the user in a conversation and sending the recommendation information to the user by sending a voice message during the conversation is executed.

[0045] Optionally, predicting the user's termination intention information based on the operation information includes:

[0046] The operation information is input into a pre-trained intention information recognition model to obtain the termination intention information output by the model.

[0047] Optionally, determining the recommended information and the order processing path corresponding to the termination instruction according to the termination intention information includes:

[0048] Inputting the termination intention information and the user profile of the user into a pre-trained information matching model, and obtaining a target processing method output by the model that matches the termination intention information;

[0049] Determine a processing rule for at least one termination instruction in the target processing method whose probability of being triggered meets a preset probability threshold, and use the processing rule as the advancement information; and use the information sending method whose probability of triggering the recommended information is greater than the preset probability threshold as the order processing path.

[0050] According to a second aspect of an embodiment of this specification, a transaction processing device is provided, including:

[0051] A receiving module, configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0052] A prediction module, configured to predict termination intention information of the user based on the operation information;

[0053] The determination module is configured to determine, based on the termination intention information, to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface.

[0054] According to a third aspect of the embodiments of this specification, a transaction processing method is provided, including:

[0055] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0056] Based on the operation information, predicting the user's termination intention information;

[0057] According to the transaction object information in the transaction order and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0058] According to a fourth aspect of the embodiments of this specification, a transaction processing device is provided, including:

[0059] An instruction receiving module is configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0060] an information prediction module, configured to predict the user's termination intention information based on the operation information;

[0061] The information determination module is configured to determine, based on the transaction object information in the transaction order and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list.

[0062] According to a fifth aspect of the embodiments of this specification, a transaction processing method is provided, including:

[0063] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0064] Based on the operation information, predicting the user's termination intention information;

[0065] According to the historical transaction data of the user, the attribute data of the user and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0066] According to a sixth aspect of the embodiments of this specification, there is provided a transaction processing device, including:

[0067] A termination instruction receiving module, configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0068] an intention information prediction module, configured to predict termination intention information of the user based on the operation information;

[0069] The intention information determination module is configured to determine to display an operation interface carrying a transaction object recommendation list to the user based on the user's historical transaction data, the user's attribute data and the termination intention information.

[0070] According to a seventh aspect of the embodiments of this specification, there is provided an information recommendation method, including:

[0071] Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user;

[0072] Based on the refund application information, predict the user's refund intention information;

[0073] Based on the refund intention information, determine to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan.

[0074] Optionally, the client receives the order processing solution, renders a recommendation page based on the order processing solution, and displays the page to the user.

[0075] According to an eighth aspect of the embodiments of this specification, there is provided an information recommendation device, including:

[0076] An instruction receiving module is configured to receive a refund instruction initiated by a client for a transaction order, wherein the refund instruction includes refund application information input by a user;

[0077] an identification module configured to predict the user's refund intention information based on the refund application information;

[0078] The determination module is configured to determine, based on the refund intention information, to send an order processing solution carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing solution.

[0079] According to a ninth aspect of the embodiments of this specification, another information recommendation method is provided, including:

[0080] Receiving a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund application information input by the user;

[0081] Sending the refund instruction to a processing platform;

[0082] An order processing solution carrying recommendation information returned by the processing platform is received, and a recommendation page is rendered based on the order processing solution and displayed to the user.

[0083] According to a tenth aspect of an embodiment of this specification, another information recommendation device is provided, including:

[0084] A receiving module, configured to receive a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund information input by the user;

[0085] An instruction sending module is configured to send the refund instruction to a processing platform;

[0086] The page display module is configured to receive the order processing solution carrying the recommendation information returned by the processing platform, render the recommendation page based on the order processing solution, and display it to the user.

[0087] According to an eleventh aspect of the embodiments of this specification, there is provided a computing device, including:

[0088] Memory and processor;

[0089] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0090] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0091] Based on the operation information, predicting the user's termination intention information;

[0092] Based on the termination intention information, determine to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface.

[0093] According to a twelfth aspect of the embodiments of this specification, a computing device is provided, including:

[0094] Memory and processor;

[0095] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0096] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0097] Based on the operation information, predicting the user's termination intention information;

[0098] According to the transaction object information in the transaction order and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0099] According to a thirteenth aspect of the embodiments of this specification, a computing device is provided, including:

[0100] Memory and processor;

[0101] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0102] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0103] Based on the operation information, predicting the user's termination intention information;

[0104] According to the historical transaction data of the user, the attribute data of the user and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0105] According to a fourteenth aspect of the embodiments of this specification, there is provided a computing device, including:

[0106] Memory and processor;

[0107] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0108] Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user;

[0109] Based on the refund application information, predict the user's refund intention information;

[0110] Based on the refund intention information, determine to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan.

[0111] According to a fifteenth aspect of the embodiments of this specification, a computing device is provided, including:

[0112] Memory and processor;

[0113] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions:

[0114] Receiving a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund application information input by the user;

[0115] Sending the refund instruction to a processing platform;

[0116] An order processing solution carrying recommendation information returned by the processing platform is received, and a recommendation page is rendered based on the order processing solution and displayed to the user.

[0117] According to the sixteenth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the transaction processing method are implemented.

[0118] According to the seventeenth aspect of the embodiments of the present specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the another transaction processing method are implemented.

[0119] According to the eighteenth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the further transaction processing method are implemented.

[0120] According to the nineteenth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the information recommendation method are implemented.

[0121] According to the twentieth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the another information recommendation method are implemented.

[0122] In one embodiment of the present specification, a termination instruction initiated by a user for a transaction order is received, wherein the termination instruction includes operation information input by the user; based on the operation information, the termination intention information of the user is predicted; based on the termination intention information, an order operation interface carrying recommendation information is determined to be displayed to the user, so that the user processes the termination operation of the transaction order according to the order operation interface;

[0123] After the user initiates a termination instruction, the user's termination intention information is determined, recommendation information is determined based on the termination intention information, and the recommendation information is sent to the user through the corresponding order processing path, so as to guide the user to cancel the termination instruction through the recommendation information, and select a better order processing method based on the recommendation information, which is conducive to reducing the number of orders with interrupted processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0124] Figure 1 is a processing flow chart of a transaction processing method provided by an embodiment of this specification;

[0125] Figure 2 is a schematic diagram of an electronic card provided by an embodiment of this specification;

[0126] Figure 3 is a schematic diagram of another electronic card provided by an embodiment of this specification;

[0127] Figure 4 It is a schematic diagram of an order follow-up record sheet provided by an embodiment of this specification;

[0128] Figure 5 is a schematic diagram of a refund initiation page provided by an embodiment of this specification;

[0129] Figure 6 It is a flow chart of a process of applying a transaction processing method provided by an embodiment of this specification to a transaction scenario;

[0130] Figure 7 is a processing flow chart of an information recommendation method provided by an embodiment of this specification;

[0131] Figure 8 is a processing flow chart of another information recommendation method provided by an embodiment of this specification;

[0132] Fig. 9 This is a schematic diagram of a scenario of an information recommendation process provided by an embodiment of this specification;

[0133] Fig.10 is a schematic diagram of a transaction processing device provided by one embodiment of the present specification;

[0134] Fig.11 is a schematic diagram of an information recommendation device provided by an embodiment of this specification;

[0135] Fig.12 is a schematic diagram of another information recommendation device provided by an embodiment of this specification;

[0136] Fig.13 is a structural block diagram of a first computing device provided by an embodiment of this specification;

[0137] Fig.14 is a structural block diagram of a second computing device provided by an embodiment of this specification;

[0138] Fig.15 is a structural block diagram of a third computing device provided by an embodiment of this specification;

[0139] Fig.16 This is a structural block diagram of a fourth computing device provided by an embodiment of this specification

[0140] Fig.17 It is a structural block diagram of a fifth computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0141] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0142] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0143] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0144] In this specification, a transaction processing method is provided. This specification also involves a transaction processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0145] Figure 1 A processing flow chart of a transaction processing method provided according to an embodiment of the present specification is shown, including steps 102 to 106.

[0146] With the rapid development of Internet technology, shopping through Internet platforms is becoming more and more common, and Internet platforms make it more convenient and diverse for users to purchase goods. In the process of trading goods through Internet platforms, after buyers pay the consumption amount to the Internet platform, they may need to refund due to various reasons. Usually, for refund applications initiated by buyers, the seller's processing methods are mainly: after receiving the refund request, determine the refund amount and refund path according to the refund request, and refund based on the refund path; after the buyer initiates the refund request, no effective measures are taken to provide goods that are more in line with user needs or of higher quality, thereby reducing the time for users to re-search for the required goods and saving computing resources.

[0147] Based on this, an embodiment of the present specification provides a transaction processing method, which receives a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes processing information entered by the user, determines the user's intention information based on the processing information, determines the order processing result corresponding to the termination instruction based on the intention information, and displays it to the user based on the order processing result.

[0148] By determining the user's intention information and determining the order processing result based on the intention information, the order processing result is used to guide the user to reselect an order processing method that is more in line with the user's intention. If the user confirms that he accepts the processing method regarding the termination instruction in the order processing result, the termination instruction is canceled.

[0149] Step 102: receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user.

[0150] Specifically, if the transaction order is generated by a user using a certain amount of funds to purchase goods, and the processing status of the transaction order is incomplete (paid but not shipped, shipped but not signed for, signed for but not confirmed), then the termination instruction may include a refund instruction or a refund and return instruction, etc. The operation information may include refund application information, usually the reason for the refund and the receipt status of the goods, etc., and may also include the user's basic attribute information and the payment account number, etc. After receiving the termination instruction initiated by the user, the user's termination intention information can be identified.

[0151] Step 104: predicting the user's termination intention information based on the operation information.

[0152] Specifically, intention means the desire to achieve a certain purpose. Upon receiving a termination instruction initiated by a user for a transaction order, in order to reduce the proportion of terminated orders in the total number of orders, the user's termination intention information can be identified based on the operation information entered by the user for the transaction order, and matching recommendation information can be determined based on the identification result, so as to guide the user to convert the terminated order into other order processing methods acceptable to the user through the recommendation information.

[0153] After determining the user's termination intention information, the order processing result can be determined based on the termination intention information. The order processing result includes recommendation information corresponding to the termination instruction and the order processing path, so as to guide the user to no longer apply for order termination or reduce the number of terminated orders through the information content of the recommendation information.

[0154] In specific implementation, the user's termination intention information can be obtained through an intention information recognition model, that is, the operation information is input into a pre-trained intention information recognition model to obtain the termination intention information output by the model.

[0155] In actual applications, the user's historical terminated order data, the transaction object information contained in the transaction order involved in the user's termination instruction, the user's attribute information, and the order processing method selected by the user for the transaction order involved in the termination instruction can be obtained; the historical terminated order data includes the resource quota involved in the termination order, the number of times the termination instruction was initiated, etc.

[0156] The user's historical terminated order data, the transaction object information and user attribute information contained in the transaction order involved in the termination instruction initiated by the user are used as training samples, and the order processing method selected by the user for the transaction order involved in the termination instruction is used as a training label to train a pre-established initial intention recognition information model to obtain the intention information recognition model, which associates the user's historical terminated order data, transaction object information and user attribute information with the order processing method.

[0157] Specifically, the intent information recognition model can be a natural language processing (NLP) model. In practical applications, it is necessary to first build a corpus and collect user portraits and the order processing method selected by the user for the transaction order involved in initiating the termination instruction, which are stored in the NLP corpus as NLP text corpus. After collecting enough NLP text corpus, the NLP text corpus is processed. The data processing can include normalization processing such as word segmentation and data cleaning to generate target NLP text corpus, and the target NLP text corpus is input into the word vector model for model training to obtain a natural language processing model.

[0158] During the use of the natural language processing model, the operation information entered by the user in the termination instruction can be processed (word segmentation, data cleaning, etc.), and the processed data can be input into the natural language processing model to obtain the natural language processing results (intention information recognition results) output by the model; intention recognition through the NLP model is conducive to improving the accuracy of the recognition results.

[0159] Taking the termination instruction as a refund instruction as an example, in order to guide the user to choose other acceptable order processing methods that can replace the termination order processing method, after receiving the refund instruction initiated by the user, the user's refund intention can be determined based on the refund application information contained in the refund instruction. If the refund application information includes "the price of the product was reduced after it was purchased", it can be determined that the user's refund intention may be "hope to refund the price difference or get some preferential compensation"; if the refund application information includes "the product is damaged", it can be determined that the user's refund intention may be "hope to receive an intact product".

[0160] Identifying the user's termination intention information through an intention information recognition model is helpful to improving the accuracy of the recognition result of the termination intention information.

[0161] Step 106: Based on the termination intention information, determine to display an order operation interface carrying recommendation information to the user, so that the user can process the termination operation of the transaction order according to the order operation interface.

[0162] Specifically, after obtaining the predicted result of the user's termination intention information, the recommended information and order processing path corresponding to the termination instruction can be determined based on the termination intention information, and the recommended information can be sent and displayed to the user according to the order processing path, so as to guide the user to cancel the termination instruction through the order processing method.

[0163] If termination of the order is used as an order processing method for the transaction order, the order processing method contained in the recommended information can be used to guide the user to cancel the termination instruction and use the order processing method in the recommended information to process the transaction order; taking the termination instruction as a refund instruction as an example, the order processing method contained in the recommended information can be making up the price difference, issuing coupons or reissuing goods, etc.

[0164] In addition, the order processing path is the channel for sending the recommendation information to the user; in actual application, the order processing path may include two types, namely, an online path (sending an order processing page / sending an information component) or an offline path (making a phone call / sending a text message). After determining the order processing path, the recommendation information can be sent according to the order processing path. If the user confirms to accept the recommendation information, the recommendation information is triggered and the termination instruction can be canceled.

[0165] After receiving a termination instruction initiated by the user and determining the user's termination intention information based on the operation information input by the user, the corresponding recommendation information can be determined based on the termination intention information, and the order processing path can be determined in combination with the termination intention information and the user's online activity level, and the recommendation information can be sent to the user through the order processing path, so as to reduce the user's willingness to terminate the order through the recommendation information, thereby reducing the number of terminated orders.

[0166] Still taking the termination instruction as a refund instruction as an example, if the refund application information includes "the price of the product has dropped after it was purchased", it can be determined that the user's refund intention includes "hope to refund the price difference or get some preferential compensation", and it can be determined that the recommended information can include "the price difference can be refunded, do you want to cancel the refund" or "a coupon of xx amount can be issued to you, do you want to cancel the refund"; if the refund application information includes "the product is damaged", it can be determined that the user's refund intention includes "hope to receive an intact product", and it can be determined that the recommended information can include "a new product can be reissued to you, do you want to cancel the refund".

[0167] After determining the recommendation information, the order processing path can also be determined in combination with the termination intention information and the user's online activity level. For example, if the user's refund intention includes "hoping to refund the price difference or get some preferential compensation", and the user's online activity level is higher than the preset threshold, the recommendation information will be sent to the user through the online path. If the user's refund intention includes "hoping to receive an intact product", and the user's online activity level is lower than the preset threshold, the recommendation information will be sent to the user through the offline path.

[0168] In specific implementation, the recommended information and order processing path corresponding to the termination instruction are determined according to the termination intention information, which can be implemented in the following ways:

[0169] Acquire a matching relationship between the termination intention information and a processing method of the termination instruction;

[0170] Determining a target processing method that matches the termination intention information according to the matching relationship;

[0171] Determine a processing rule for at least one termination instruction in the target processing method whose probability of being triggered meets a preset probability threshold, and use the processing rule as the recommended information, and use the information sending method in which the probability of the recommended information being triggered is greater than the preset probability threshold as the order processing path.

[0172] Specifically, if the recommended information (processing rule) matching the termination instruction is triggered, it indicates that the user confirms to accept the processing rule. Therefore, it is necessary to select the processing rule whose triggering probability meets the preset probability threshold in the target processing method matching the termination intention information as the recommended information, and the processing rule whose triggering probability meets the preset probability threshold can be one or more. If there are multiple processing rules, multiple processing rules can be sent to the user for selection.

[0173] After determining the recommendation information, it is also necessary to determine the order processing path for the recommendation information, that is, to determine whether to send the recommendation information to the user online or offline. The choice of path is still based on the probability of the user receiving and triggering the recommendation information through the path, that is, the information sending method with a triggering probability of the recommendation information greater than a preset probability threshold is selected as the order processing path.

[0174] In addition, the information matching model can be used to obtain the processing method of the termination instruction that matches the termination intention information, which can be implemented in the following ways:

[0175] Inputting the termination intention information and the user profile of the user into a pre-trained information matching model, and obtaining a target processing method output by the model that matches the termination intention information;

[0176] Determine a processing rule for at least one termination instruction in the target processing method whose probability of being triggered meets a preset probability threshold, and use the processing rule as the recommended information; and use an information sending method whose probability of being triggered of the recommended information is greater than the preset probability threshold as the order processing path.

[0177] Specifically, the user portrait includes the user's basic attribute information (gender, age, occupation, etc.) and the user's historical data on the platform (browsing history, consumption history, etc.). By matching the termination intention information and the user portrait input information to the model, the target processing method of the model output is obtained;

[0178] In the matching relationship between the pre-configured termination intention information and the processing method of the termination instruction, if there are multiple processing methods that match one termination intention information, the target processing method is determined in combination with the user portrait and the termination intention information, so that the probability of triggering at least one processing rule in the target processing method is higher, which is more conducive to reducing the return rate.

[0179] According to the termination intention information, the recommendation information to be sent to the user and the order processing path of the recommendation information are determined, so as to guide the user not to apply for termination of the order or to reduce the number of terminated orders through the information content of the recommendation information.

[0180] Furthermore, after the order operation interface is displayed to the user according to the order processing path, it is necessary to determine whether to cancel the termination instruction according to the user's feedback, which can be specifically achieved in the following ways:

[0181] Receiving feedback information submitted by the user based on the order operation interface;

[0182] In the case where it is determined according to the feedback information that the user confirms to accept the recommendation information, it is determined that the recommendation information is triggered, and the termination instruction is cancelled.

[0183] Specifically, after sending the recommendation information to the user, feedback information submitted by the user regarding the recommendation information can be received. Since the recommendation information contains the processing rules for the termination instruction, the user can return feedback information regarding whether he or she agrees to be processed according to the processing rules. Therefore, when the feedback information is received, it can be determined based on the feedback information whether the user confirms acceptance (whether he or she agrees). If he or she accepts, the termination instruction is canceled.

[0184] Still taking the termination instruction as a refund instruction as an example, if the recommendation information includes "the price difference can be refunded, do you want to cancel the refund" or "a coupon of xx amount can be issued to you, do you want to cancel the refund", after sending the recommendation information to the user according to the order processing path, if the feedback information returned by the user is "yes", the refund will be stopped or canceled.

[0185] In addition, the above is a situation where the termination instruction can be canceled according to the feedback information. The situation where the termination instruction cannot be canceled is as follows:

[0186] a) executing the termination instruction when no feedback information submitted by the user for the recommendation information is received;

[0187] b) receiving feedback information submitted by the user regarding the recommendation information, and if it is determined according to the feedback information that the user refuses to accept the recommendation information, and if it is determined that the recommendation information is not triggered, executing the termination instruction.

[0188] Specifically, if no feedback from the user is received after the recommendation information is sent to the user, the termination instruction needs to be executed; in actual applications, a delayed processing time can be set for the termination instruction, that is, after receiving the termination instruction initiated by the user, the user's termination intention information can be determined first, and the recommendation information can be determined based on the termination intention information. After the recommendation information is sent to the user, if no feedback from the user is received after the delayed processing time of the termination instruction, the termination instruction is executed; or, feedback from the user is received, and the processing rule that the user refuses to accept the termination instruction contained in the recommendation information is determined based on the feedback information, and the termination instruction is executed.

[0189] Continuing with the above example, if the recommendation information includes "the price difference can be refunded, do you want to cancel the refund" or "a coupon of xx amount can be issued to you, do you want to cancel the refund", after sending the recommendation information to the user according to the order processing path, if no feedback information from the user is received after the delayed processing time (10 minutes) of the termination instruction, a refund will be made to the user; or, if the feedback information returned by the user is "no", a refund will be made to the user.

[0190] Furthermore, since the order processing path includes an online path or an offline path, when it is determined that the order processing path is an online path, an order operation interface carrying the recommendation information is displayed to the user according to the order processing path, which can be specifically implemented in the following manner:

[0191] Performing interface rendering based on the recommendation information, generating an order operation interface and displaying it to the user; the order operation interface includes clickable controls;

[0192] Correspondingly, after displaying the order operation interface carrying the recommendation information to the user according to the order processing path, the method further includes:

[0193] Detecting a click operation performed by the user on the order operation interface;

[0194] In the case where it is detected that the user submits a confirmation instruction by clicking the clickable control, the recommendation information is triggered and the termination instruction is cancelled; or

[0195] In the case where the user does not click on the clickable control, the termination instruction is executed.

[0196] Specifically, one form of sending recommendation information to users through an online path is to send the recommendation information by displaying an order operation interface to the user (the order operation interface contains the recommendation information). Therefore, after determining the recommendation information and determining that the order processing path is an online path, the interface can be rendered based on the recommendation information, and the rendered order operation interface can be displayed to the user. The order operation interface contains clickable controls, and the user can submit feedback information by clicking the controls to indicate whether to accept the processing rules of the termination instruction contained in the recommendation information.

[0197] Therefore, after displaying the order operation interface to the user, it is also necessary to detect the user's click operation on the order operation interface. When it is detected that the user submits a confirmation instruction by clicking the control, it indicates that the user accepts the processing rules, then the recommendation information is triggered and the termination instruction can be canceled; if the user's click operation on the control is not received, the termination instruction is executed.

[0198] Furthermore, in order to improve the user's service experience, it is necessary to reduce the number of times the order operation interface is displayed to the user. In specific implementation, it can be set to display the order operation interface to the user only once for the same transaction order. Therefore, before sending the recommendation information to the user according to the order processing path, it is also necessary to query the historical display records of displaying the order operation interface to the user for the transaction order; if the query result is empty, the recommendation information is sent to the user according to the order processing path.

[0199] In addition, another form of sending recommendation information to users through online paths is to send recommendation information to users in the form of information components, which can be implemented in the following ways:

[0200] Determine a component template of a component to be displayed corresponding to the recommendation information;

[0201] The component template is rendered using the recommendation information as rendering data to generate an information display component, which is then displayed to the user through an information interaction window; the information interaction window includes clickable controls.

[0202] Specifically, since different recommended information contains different processing rules for termination instructions, and different processing rules may have different display methods, after determining the recommended information and determining that the order processing path is an online path, the component template of the corresponding component to be displayed can be determined based on the recommended information, and the recommended information is used as rendering data to render the component template, and the rendered information display component is sent to the user through the information interaction window (the chat window between customer service and the user). The information display component contains clickable controls, and the user can submit feedback by clicking the controls to indicate whether he accepts the processing rules contained in the recommended information.

[0203] Therefore, after sending the information display component to the user, it is also necessary to detect the user's click operation on the information display component. When it is detected that the user submits a confirmation instruction by clicking the control, it indicates that the user accepts the processing rules, then the recommendation information is triggered and the termination instruction can be canceled; if the user's click operation on the control is not received, the termination instruction is executed.

[0204] In practical applications, the information display component may be an electronic card. That is, taking the termination instruction as a refund instruction as an example, the schematic diagram of the electronic card issued to the user is as follows: Figure 2 As shown by Figure 2 It can be seen that the processing rule of the termination instruction is to issue a coupon to the user. Therefore, the card can contain a link to receive the coupon. If the user clicks to receive the coupon, it means that the user accepts the processing rule of the termination instruction and the refund can be cancelled. Alternatively, a schematic diagram of another electronic card issued to the user is as follows: Figure 3 As shown by Figure 3 It can be seen that the processing rule of the termination instruction is to refund the price difference to the user. If the user clicks the control "Yes", the refund will be canceled; if no feedback information is received from the user after the delayed processing time (10 minutes) of the termination instruction, the user will be refunded; or, if the feedback information returned by the user is "No", the user will be refunded.

[0205] In addition, when it is determined that the order processing path is an offline path, the recommendation information is sent to the user according to the order processing path, which can be specifically implemented in the following manner:

[0206] Calling a conversation interface to interact with the user, and sending the recommendation information to the user by sending a voice message during the conversation;

[0207] Receiving voice information and / or key feedback information returned by the user during the conversation;

[0208] If it is determined according to the voice information and / or the key feedback information that the user confirms to accept the recommendation information, the recommendation information is triggered and the termination instruction is cancelled; or

[0209] If it is determined according to the voice information and / or the key feedback information that the user refuses to accept the recommendation information, the recommendation information is not triggered and the termination instruction is executed.

[0210] Specifically, one form of sending recommendation information to users through offline channels is outbound calling (making a phone call), that is, calling the outbound call session interface to interact with the user in a conversation, and sending the recommendation information in a conversational manner, and reminding the user to return feedback information on the recommendation information through a voice message during the conversation, and the feedback information can be returned in the form of voice or keystrokes; when the feedback information is received, it can be determined whether the user confirms the acceptance based on the feedback information. If accepted, the termination instruction is canceled; if not accepted, the termination instruction is executed; or, if no feedback information is received, the termination instruction is executed.

[0211] Still taking the termination instruction as a refund instruction as an example, if the recommendation information is "the price difference is refundable, do you want to cancel the refund", the recommendation information is sent to the user in the form of a voice message, and the user is reminded to return feedback information by pressing keys (press "1" to confirm acceptance, press "2" to refuse acceptance). If no feedback information is received from the user, a refund is made to the user; or, if the key information returned by the user is "2", a refund is made to the user; if the key information returned by the user is "1", the refund is canceled.

[0212] After sending recommendation information to users through offline channels, an order follow-up record sheet can be created based on user information, user feedback information and outbound call data (outbound call content, call duration, etc.).

[0213] Still taking the termination instruction as a refund instruction as an example, the refund application information entered by the user is "the size is too large", the refund intention is identified based on the refund application information, and the recommended information is determined to be "re-shipment" based on the identification result. The order processing path is an offline path (the user's online activity is low), and the recommendation information is sent through an outbound call. According to the feedback information returned by the user, it is determined that the user accepts the processing method of "re-shipment", and the size information is supplemented. The user's feedback information and the schematic diagram of the order follow-up record sheet created by the outbound call data are as follows: Figure 4 As shown, through Figure 4 You can obtain detailed records of outbound calls, size information supplemented by the user, and the user's delivery address and other information.

[0214] The record sheet can be used to obtain the user's basic information and order processing method, which provides convenience for subsequent processing and helps improve order processing efficiency.

[0215] In addition, another form of sending recommendation information to users through offline channels is sending the recommendation information through text messages. After receiving the recommendation information in the form of text messages, the user can submit feedback information by sending text messages.

[0216] Furthermore, in order to improve the user's service experience, it is necessary to reduce the number of outbound calls to the user. In specific implementation, a fixed outbound call time can be set, as well as the number of outbound calls to the user within a fixed time period. Therefore, before sending the recommendation information to the user according to the order processing path, it is necessary to determine the session interaction time for the session interaction with the user, and determine whether the session interaction time belongs to a preset time interval; if so, query the interaction record of the session interaction with the user within the preset time period, and determine whether the interaction record is empty; if the interaction record is empty, send the recommendation information to the user according to the order processing path.

[0217] Specifically, before sending the recommendation information to the user according to the order processing path, it is necessary to determine whether the outbound call time meets the conditions and whether the number of outbound calls of the user within the preset time period reaches the upper limit. The embodiment of this specification sets the upper limit of the number of outbound calls of the user within the preset time period to once. In actual applications, the upper limit of the number of outbound calls of the user within the preset time period can be determined according to actual needs, and no restrictions are made here.

[0218] In addition, the transaction processing method provided in the embodiment of this specification is to retain the user after initiating a refund application. In actual application, the refund retention can also be performed on the user's refund initiation page. The schematic diagram of the refund initiation page is as follows: Figure 5 As shown, Figure 5 In addition to refund-related information (refund reason, number of refunds, refund amount, etc.), this page can also display refund prompt information to users to reduce the probability of refunds. In actual applications, the refund prompt information can be "The seller has received or can confirm the refund, please communicate with the seller", and the seller can retain the refund after the buyer initiates a communication request.

[0219] During specific implementation, the processing platform can provide an information configuration interface for the order processor, and the order processor can configure different processing methods for different termination intention information, that is, there is a matching relationship between the termination intention information and the processing method. For one type of termination intention information, the processing method that matches it can include at least one processing rule, and each processing rule corresponds to a different probability of being triggered.

[0220] In addition, the processing platform can also provide a reminder service for the order processor to remind the user to update the above-mentioned pre-configured processing method, or when the processing platform determines based on the feedback information that the user refuses to accept the recommended information, the processing platform can remind the order processor to adjust the order processing method based on the user's termination intention information to improve user retention rate.

[0221] After the user initiates a termination instruction, the embodiment of the present specification determines the user's termination intention information, determines recommendation information based on the termination intention information, and sends the recommendation information to the user through the corresponding order processing path, so as to attract the user to cancel the termination instruction through the recommendation information, thereby guiding the user to choose a more optimized order processing method, which is conducive to reducing the number of order terminations.

[0222] The following combination Figure 6 , taking the application of the transaction processing method provided in this specification in a transaction scenario as an example, the transaction processing method is further explained. Figure 6 A flowchart of a process of applying a transaction processing method provided by an embodiment of the present specification to a transaction scenario is shown, and the specific steps include step 602 to step 622.

[0223] Step 602: Receive a refund application submitted by the buyer for the transaction order, wherein the refund application includes refund application information entered by the buyer.

[0224] Step 604: input the refund application information into a pre-trained intention recognition model to obtain the refund intention output by the model.

[0225] Step 606: Input the refund intention and the user profile of the buyer into a pre-trained recommendation model to obtain a target processing method output by the model that matches the refund intention.

[0226] Step 608, determining at least one return task processing rule in the target processing method whose triggering probability meets a preset probability threshold, and using the return task processing rule as recommendation information for transaction recommendation to the buyer.

[0227] Step 610: Determine a recommended path for sending the recommendation information to the buyer based on the buyer's online activity.

[0228] Specifically, if it is determined that the recommendation is to be made by an outbound call, step 612 is executed; if it is determined that the recommendation is to be made by issuing a card, step 616 is executed.

[0229] Step 612: determine the card template of the card to be displayed corresponding to the recommendation information.

[0230] Step 614, using the recommendation information as rendering data, rendering the card template, generating a transaction recommendation card, and displaying it to the buyer through an information interaction window.

[0231] Step 616, calling the conversation interface to interact with the buyer, and sending the recommendation information to the buyer by sending a voice message during the conversation.

[0232] Step 618: receiving feedback information submitted by the buyer regarding the recommendation information.

[0233] Step 620: When it is determined according to the feedback information that the buyer confirms acceptance, it is determined that the recommendation information is triggered and the return task is interrupted.

[0234] Step 622: If no feedback information submitted by the buyer regarding the recommendation information is received, or if it is determined based on the feedback information that the buyer refuses to accept the recommendation information, it is determined that the recommendation information is not triggered, then the return task is executed.

[0235] In one embodiment of the present specification, after a buyer initiates a refund application, the buyer's refund intention is identified, recommendation information matching the identification result is determined, and the recommendation information is sent to the buyer through a corresponding recommendation path, so as to attract the buyer to cancel the refund through the recommendation information, thereby reducing the refund amount or refund rate.

[0236] An embodiment of this specification provides a specific implementation process of another transaction processing method, including the following steps:

[0237] Step 1: receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0238] Step 2: predicting the user's termination intention information based on the operation information;

[0239] Step three: According to the transaction object information in the transaction order and the termination intention information, determine to display an operation interface carrying a transaction object recommendation list to the user.

[0240] Specifically, the transaction processing method described in the embodiments of this specification is applied to the order processing party. If the transaction order is generated by a user using a certain amount of funds to purchase goods, and the processing status of the transaction order is incomplete (paid but not shipped, shipped but not signed for, signed for but not confirmed), then the termination instruction may include a refund instruction or a refund and return instruction, etc. The operation information may include refund application information, usually the reason for the refund and the receipt status of the goods, etc., and may also include basic attribute information of the user and the payment account number and other information;

[0241] After receiving the termination instruction initiated by the user, the order processor can identify the user's termination intention information; after obtaining the identification result of the termination intention information, it can recommend other transaction objects of the same type to the user based on the termination intention information and the transaction object information in the transaction order, so as to improve the user retention rate.

[0242] Taking the termination instruction as a refund instruction as an example, the order processing party is the merchant. After receiving the refund instruction initiated by the user, the merchant can determine the user's refund intention based on the refund application information contained in the refund instruction. If the refund application information includes "the size of clothes A I took is too large", it can be determined that the user's refund intention may be "I hope to buy clothes of the right size"; if the merchant receives this refund instruction and determines that clothes A is out of stock, the merchant can recommend other clothes of the same type as clothes A that are in sufficient supply to the user, so as to retain the user.

[0243] In the embodiment of the present specification, after the user initiates a termination instruction, the termination intention information of the user is determined, and recommendation information is determined according to the termination intention information, so as to improve the retention rate of the user through the recommendation information, thereby facilitating an increase in the transaction volume between the user and the merchant.

[0244] An embodiment of the present specification provides a specific implementation process of another transaction processing method, including the following steps:

[0245] Step 1: receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0246] Step 2: predicting the user's termination intention information based on the operation information;

[0247] Step three: Determine to display an operation interface carrying a transaction object recommendation list to the user based on the user's historical transaction data, the user's attribute data, and the termination intention information.

[0248] Specifically, the transaction processing method described in the embodiments of this specification is applied to a processing platform. If the transaction order is generated by a user using a certain amount of funds to purchase goods, and the processing status of the transaction order is incomplete (paid but not shipped, shipped but not signed for, signed for but not confirmed), then the termination instruction may include a refund instruction or a refund and return instruction, etc. The operation information may include refund application information, usually the reason for the refund and the receipt status of the goods, etc., and may also include basic attribute information of the user and information such as the payment account number;

[0249] After receiving a termination instruction initiated by the user, the processing platform can identify the user's termination intention information. After obtaining the identification result of the termination intention information, it can determine and recommend to the user other transaction objects of the same or different types in the processing platform based on the termination intention information, the user's historical transaction data and the user's attribute data, so as to improve the user's retention rate in the processing platform.

[0250] Taking the termination instruction as a refund instruction as an example, after receiving the refund instruction initiated by the user, the processing platform can determine the user's refund intention based on the refund application information contained in the refund instruction. If the refund application information includes "the price of the product was reduced after it was purchased", it can be determined that the user's refund intention may be "hope to refund the price difference or get some preferential compensation"; after receiving the user's refund instruction, the processing platform can determine the user's preferences based on the user's historical transaction data, the user's attribute data and the refund intention, and issue coupons for products related to the user's preferences in other stores on the processing platform according to the user's preferences.

[0251] In the embodiment of the present specification, after the user initiates a termination instruction, the termination intention information of the user is determined, and recommendation information is determined according to the termination intention information, so as to improve the retention rate of the user through the recommendation information, thereby facilitating an increase in the transaction volume between the user and the merchant.

[0252] Figure 7 A processing flow chart of an information recommendation method provided according to an embodiment of the present specification is shown, including steps 702 to 706.

[0253] Step 702: Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user.

[0254] Step 704: predict the user's refund intention information based on the refund application information.

[0255] Step 706: Based on the refund intention information, determine to display an order processing plan with recommendation information to the user, so that the user can process the refund operation of the transaction order according to the order processing plan.

[0256] An information recommendation method provided in an embodiment of the present specification is applied to a processing platform, wherein the processing platform receives a refund instruction initiated by a user for a transaction order through a client, determines the user's refund intention information based on the refund application information contained in the refund instruction, determines recommended information based on the refund intention information, and recommends information to the user based on the recommended information, that is, sends an order processing plan carrying the recommended information to the client, and the client receives and renders a recommendation page based on the order processing plan and displays it to the user.

[0257] In the embodiments of the present specification, after the user initiates a refund instruction, the refund intention information of the user is determined, the recommendation information is determined according to the refund intention information, and an order processing plan carrying the recommendation information is sent to the client. The client renders a recommendation page based on the order processing plan and displays it to the user, so as to attract the user to cancel the refund instruction through the recommendation information, thereby guiding the user to choose a more optimized order processing method, which is conducive to reducing the refund amount or refund rate.

[0258] Figure 8 A processing flow chart of a transaction processing method provided according to an embodiment of the present specification is shown, including steps 802 to 806.

[0259] Step 802: Receive a refund instruction initiated by the user for the transaction order, wherein the refund instruction includes refund application information input by the user.

[0260] Step 804, sending the refund instruction to the processing platform.

[0261] Step 806: Receive the order processing solution carrying the recommendation information returned by the processing platform, render a recommendation page based on the order processing solution, and display it to the user.

[0262] The information recommendation method provided in the embodiments of this specification is applied to a client, and the client is used to receive a refund instruction initiated by a user for a transaction order, and send the refund instruction to a processing platform. After receiving the refund instruction, the processing platform determines the user's refund intention information based on the refund application information carried in the refund instruction, and determines an order processing plan carrying recommended information based on the refund intention information, and sends the order processing plan to the client. After receiving the order processing plan, the client generates an information recommendation page based on the order processing plan and displays it to the user.

[0263] The scenario diagram of the information recommendation process between users, clients and processing platforms is as follows: Fig. 9 As shown, the user initiates a termination instruction to the processing platform through the client. After receiving the termination instruction, the processing platform determines the user's termination intention information based on the operation information carried in the termination instruction, and determines the order operation interface carrying the recommended information based on the termination intention information, and sends the order operation interface to the client. The client receives and displays the order operation interface to the user.

[0264] After the user initiates a termination instruction, the embodiment of the present specification determines the user's termination intention information, determines recommended information based on the termination intention information, and sends the recommended information to the user through the corresponding order processing path, so as to attract the user to cancel the termination instruction through the recommended information, thereby guiding the user to choose a more optimized order processing method, which is conducive to reducing the return amount or return rate.

[0265] Corresponding to the above-mentioned transaction processing method embodiment, this specification also provides a transaction processing device embodiment, Fig.10 FIG. 1 is a schematic diagram of a transaction processing device provided by an embodiment of the present specification. Fig.10 As shown, the device comprises:

[0266] The receiving module 1002 is configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0267] A prediction module 1004 is configured to predict the user's termination intention information based on the operation information;

[0268] The determination module 1006 is configured to determine, based on the termination intention information, to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface.

[0269] Optionally, the determining module 1006 includes:

[0270] a determination submodule, configured to determine the recommended information and the order processing path corresponding to the termination instruction according to the termination intention information;

[0271] The display submodule is configured to display an order operation interface carrying the recommendation information to the user according to the order processing path.

[0272] Optionally, the transaction processing device further includes:

[0273] A first feedback information receiving module is configured to receive feedback information submitted by the user based on the order operation interface;

[0274] The first interruption module is configured to, when it is determined according to the feedback information that the user confirms to accept the recommendation information, determine that the recommendation information is triggered and cancel the termination instruction.

[0275] Optionally, the transaction processing device further includes:

[0276] A first task execution module is configured to execute the termination instruction if no feedback information submitted by the user for the recommendation information is received;

[0277] A second feedback information receiving module is configured to receive feedback information submitted by the user for the recommendation information;

[0278] The second task execution module is configured to, if it is determined according to the feedback information that the user refuses to accept the recommendation information, determine that the recommendation information is not triggered, and then execute the termination instruction.

[0279] Optionally, the determining submodule includes:

[0280] a matching relationship acquisition unit, configured to acquire a matching relationship between the termination intention information and a processing method of the termination instruction;

[0281] A first determining unit is configured to determine a target processing method matching the termination intention information according to the matching relationship;

[0282] The second determination unit is configured to determine a processing rule of at least one termination instruction in the target processing method whose triggering probability meets a preset probability threshold, and use the processing rule as the recommended information, and use the information sending method whose triggering probability of the recommended information is greater than the preset probability threshold as the order processing path.

[0283] Optionally, the display submodule includes:

[0284] A first display unit is configured to perform interface rendering based on the recommendation information, generate an order operation interface and display it to the user; the order operation interface includes clickable controls;

[0285] Accordingly, the transaction processing device further includes:

[0286] A detection module, configured to detect a click operation performed by the user on the order operation interface;

[0287] A first task interruption module is configured to, when detecting that the user submits a confirmation instruction by clicking the clickable control, the recommendation information is triggered and the termination instruction is cancelled;

[0288] The first rollback task execution module is configured to execute the termination instruction if no instruction is received from the user to click on the clickable control.

[0289] Optionally, the transaction processing device further includes:

[0290] A query module, configured to query the historical display record of displaying the order operation interface to the user for the transaction order;

[0291] If the query result is empty, the display submodule is run.

[0292] Optionally, the display submodule includes:

[0293] A template determining unit, configured to determine a component template of a component to be displayed corresponding to the recommendation information;

[0294] The rendering unit is configured to use the recommendation information as rendering data, render the component template, generate an information display component, and display it to the user through an information interaction window; the information interaction window includes a clickable control.

[0295] Optionally, the determining module 1006 further includes:

[0296] A calling submodule is configured to call a conversation interface to interact with the user, and send the recommendation information to the user by sending a voice message during the conversation;

[0297] A first information receiving submodule is configured to receive voice information and / or key feedback information returned by the user during the conversation;

[0298] A second task interruption submodule is configured to, if it is determined according to the voice information and / or the key feedback information that the user confirms to accept the recommendation information, then the recommendation information is triggered and the termination instruction is cancelled;

[0299] The second fallback task execution submodule is configured to execute the termination instruction if it is determined according to the voice information and / or the key feedback information that the user refuses to accept the recommendation information and the recommendation information is not triggered.

[0300] Optionally, the determining module 1006 further includes:

[0301] a session interaction time determination submodule, configured to determine a session interaction time for performing a session interaction with the user;

[0302] A determination submodule, configured to determine whether the conversation interaction time falls within a preset time interval;

[0303] If the result of the operation of the judgment module is yes, then the interaction record query submodule is executed;

[0304] The interaction record query submodule is configured to query the interaction record of the conversation interaction with the user within a preset time period, and determine whether the interaction record is empty;

[0305] If the interaction record is empty, the calling submodule is executed.

[0306] Optionally, the prediction module 1004 is further configured to:

[0307] The operation information is input into a pre-trained intention information recognition model to obtain the termination intention information output by the model.

[0308] Optionally, the determining submodule includes:

[0309] An acquisition unit is configured to input the termination intention information and the user portrait of the user into a pre-trained information matching model, and acquire a target processing method output by the model that matches the termination intention information;

[0310] The third determination unit is configured to determine a processing rule of at least one termination instruction in the target processing method whose triggering probability meets a preset probability threshold, and use the processing rule as the advancement information; and use the information sending method in which the triggering probability of the recommended information is greater than the preset probability threshold as the order processing path.

[0311] The above is a schematic scheme of a transaction processing device of this embodiment. It should be noted that the technical scheme of the transaction processing device and the technical scheme of the transaction processing method described above belong to the same concept, and the details not described in detail in the technical scheme of the transaction processing device can be found in the description of the technical scheme of the transaction processing method described above.

[0312] Corresponding to the above another transaction processing method embodiment, this specification also provides another transaction processing device embodiment, the device comprising:

[0313] An instruction receiving module is configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0314] an information prediction module, configured to predict the user's termination intention information based on the operation information;

[0315] The information determination module is configured to determine, based on the transaction object information in the transaction order and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list.

[0316] The above is a schematic scheme of another transaction processing device of this embodiment. It should be noted that the technical scheme of the transaction processing device and the technical scheme of the another transaction processing method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the transaction processing device can be referred to the description of the technical scheme of the another transaction processing method mentioned above.

[0317] Corresponding to the above-mentioned transaction processing method embodiment, this specification also provides another transaction processing device embodiment, the device comprising:

[0318] A termination instruction receiving module, configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0319] an intention information prediction module, configured to predict termination intention information of the user based on the operation information;

[0320] The intention information determination module is configured to determine to display an operation interface carrying a transaction object recommendation list to the user based on the user's historical transaction data, the user's attribute data and the termination intention information.

[0321] The above is a schematic scheme of another transaction processing device of this embodiment. It should be noted that the technical scheme of the transaction processing device and the technical scheme of the above-mentioned another transaction processing method belong to the same concept, and the details not described in detail in the technical scheme of the transaction processing device can be referred to the description of the technical scheme of the above-mentioned another transaction processing method.

[0322] Corresponding to the above method embodiment, this specification also provides an information recommendation device embodiment, Fig.11 FIG. 1 is a schematic diagram of an information recommendation device provided by an embodiment of the present specification. Fig.11 As shown, the device comprises:

[0323] The instruction receiving module 1102 is configured to receive a refund instruction initiated by the client for a transaction order, wherein the refund instruction includes refund application information input by the user;

[0324] The identification module 1104 is configured to predict the user's refund intention information based on the refund application information;

[0325] The determination module 1106 is configured to determine, based on the refund intention information, to send an order processing solution carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing solution.

[0326] Optionally, the client receives the order processing solution, renders a recommendation page based on the order processing solution, and displays the page to the user.

[0327] The above is a schematic scheme of an information recommendation device of this embodiment. It should be noted that the technical scheme of the information recommendation device and the technical scheme of the above-mentioned information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the information recommendation device can be referred to the description of the technical scheme of the above-mentioned information recommendation method.

[0328] Corresponding to the above method embodiment, this specification also provides another information recommendation device embodiment, Fig.12 FIG. 2 is a schematic diagram of another information recommendation device provided by an embodiment of the present specification. Fig.12 As shown, the device comprises:

[0329] The receiving module 1202 is configured to receive a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund information input by the user;

[0330] The instruction sending module 1204 is configured to send the refund instruction to the processing platform;

[0331] The page display module 1206 is configured to receive the order processing solution carrying the recommendation information returned by the processing platform, render the recommendation page based on the order processing solution, and display it to the user.

[0332] The above is a schematic scheme of another information recommendation device of this embodiment. It should be noted that the technical scheme of the information recommendation device and the technical scheme of the above another information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the information recommendation device can be referred to the description of the technical scheme of the above another information recommendation method.

[0333] Fig.13 The structure block diagram of the first computing device 1300 provided according to an embodiment of the present specification is shown. The components of the computing device 1300 include but are not limited to a memory 1310 and a processor 1320. The processor 1320 is connected to the memory 1310 via a bus 1330, and the database 1350 is used to store data.

[0334] The computing device 1300 also includes an access device 1340 that enables the computing device 1300 to communicate via one or more networks 1360. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1340 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0335] In one embodiment of the present specification, the above components of the computing device 1300 and Fig.13 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.13 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0336] Computing device 1300 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 1300 may also be a mobile or stationary server.

[0337] The memory 1310 is used to store computer executable instructions, and the processor 1320 is used to execute the following computer executable instructions:

[0338] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0339] Based on the operation information, predicting the user's termination intention information;

[0340] Based on the termination intention information, determine to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface.

[0341] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the transaction processing method described above are of the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the transaction processing method described above.

[0342] Fig.14 The structure block diagram of the second computing device 1400 provided according to an embodiment of the present specification is shown. The components of the computing device 1400 include but are not limited to a memory 1410 and a processor 1420. The processor 1420 is connected to the memory 1410 via a bus 1430, and the database 1450 is used to store data.

[0343] The computing device 1400 also includes an access device 1440 that enables the computing device 1400 to communicate via one or more networks 1460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0344] In one embodiment of the present specification, the above components of the computing device 1400 and Fig.14 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.14 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0345] Computing device 1400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 1400 may also be a mobile or stationary server.

[0346] The memory 1410 is used to store computer executable instructions, and the processor 1420 is used to execute the following computer executable instructions:

[0347] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0348] Based on the operation information, predicting the user's termination intention information;

[0349] According to the transaction object information in the transaction order and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0350] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned another transaction processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned another transaction processing method.

[0351] Fig.15 The structure block diagram of the third computing device 1500 provided according to an embodiment of the present specification is shown. The components of the computing device 1500 include but are not limited to a memory 1510 and a processor 1520. The processor 1520 is connected to the memory 1510 via a bus 1530, and the database 1550 is used to store data.

[0352] The computing device 1500 also includes an access device 1540 that enables the computing device 1500 to communicate via one or more networks 1560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0353] In one embodiment of the present specification, the above components of the computing device 1500 and Fig.15 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.15 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0354] Computing device 1500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 1500 may also be a mobile or stationary server.

[0355] The memory 1510 is used to store computer executable instructions, and the processor 1520 is used to execute the following computer executable instructions:

[0356] Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user;

[0357] Based on the operation information, predicting the user's termination intention information;

[0358] According to the historical transaction data of the user, the attribute data of the user and the termination intention information, it is determined to display an operation interface carrying a transaction object recommendation list to the user.

[0359] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned another transaction processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned another transaction processing method.

[0360] Fig.16 The fourth computing device 1600 provided according to an embodiment of the present specification is shown in a block diagram. The components of the computing device 1600 include but are not limited to a memory 1610 and a processor 1620. The processor 1620 is connected to the memory 1610 via a bus 1630, and the database 1650 is used to store data.

[0361] The computing device 1600 also includes an access device 1640 that enables the computing device 1600 to communicate via one or more networks 1660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0362] In one embodiment of the present specification, the above components of the computing device 1600 and Fig.16 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.16 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0363] Computing device 1600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 1600 may also be a mobile or stationary server.

[0364] The memory 1610 is used to store computer executable instructions, and the processor 1620 is used to execute the following computer executable instructions:

[0365] Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user;

[0366] Based on the refund application information, predict the user's refund intention information;

[0367] Based on the refund intention information, determine to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan.

[0368] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned information recommendation method.

[0369] Fig.17 The fourth computing device 1700 provided according to an embodiment of the present specification is shown in a block diagram. The components of the computing device 1700 include but are not limited to a memory 1710 and a processor 1720. The processor 1720 is connected to the memory 1710 via a bus 1730, and the database 1750 is used to store data.

[0370] The computing device 1700 also includes an access device 1740 that enables the computing device 1700 to communicate via one or more networks 1760. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1740 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0371] In one embodiment of the present specification, the above components of the computing device 1700 and Fig.17 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.17 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0372] Computing device 1700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 1700 may also be a mobile or stationary server.

[0373] The memory 1710 is used to store computer executable instructions, and the processor 1720 is used to execute the following computer executable instructions:

[0374] Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user;

[0375] Based on the refund application information, predict the user's refund intention information;

[0376] Based on the refund intention information, determine to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan.

[0377] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned another information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned another information recommendation method.

[0378] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of the transaction processing method when executed by a processor.

[0379] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the transaction processing method described above are of the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the transaction processing method described above.

[0380] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of the another transaction processing method when executed by a processor.

[0381] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the other transaction processing method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the other transaction processing method mentioned above.

[0382] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of the further transaction processing method when executed by a processor.

[0383] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned another transaction processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned another transaction processing method.

[0384] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of the information recommendation method when executed by a processor.

[0385] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned information recommendation method.

[0386] An embodiment of the present specification further provides a computer-readable storage medium storing computer instructions, which are used to implement the steps of another information recommendation method when executed by a processor.

[0387] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned another information recommendation method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned another information recommendation method.

[0388] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0389] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0390] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0391] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0392] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A transaction processing method, comprising: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; Based on the termination intention information, determine to display an order operation interface carrying the recommended information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface, wherein the termination intention information and the recommended information have a corresponding relationship, and different termination intention information corresponds to different recommended information; The determining, based on the termination intention information, to display an order operation interface carrying the recommendation information to the user includes: Determine the recommended information and order processing path corresponding to the termination instruction according to the termination intention information; display the order operation interface carrying the recommended information to the user according to the order processing path, and the order processing path includes an online path or an offline path.

2. The transaction processing method according to claim 1, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, it also includes: Receiving feedback information submitted by the user based on the order operation interface; In the case where it is determined according to the feedback information that the user confirms to accept the recommendation information, it is determined that the recommendation information is triggered, and the termination instruction is cancelled.

3. The transaction processing method according to claim 1, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, it also includes: In the case where no feedback information submitted by the user with respect to the recommendation information is received, executing the termination instruction; or, receiving feedback information submitted by the user regarding the recommendation information; In the case where it is determined according to the feedback information that the user refuses to accept the recommendation information, it is determined that the recommendation information is not triggered, and the termination instruction is executed.

4. The transaction processing method according to claim 1, wherein determining the recommended information and order processing path corresponding to the termination instruction according to the termination intention information comprises: Acquire a matching relationship between the termination intention information and a processing method of the termination instruction; Determining a target processing method that matches the termination intention information according to the matching relationship; Determine a processing rule for at least one termination instruction in the target processing method whose probability of being triggered meets a preset probability threshold, and use the processing rule as the recommended information, and use the information sending method in which the probability of the recommended information being triggered is greater than the preset probability threshold as the order processing path.

5. The transaction processing method according to claim 1, wherein the step of displaying an order operation interface carrying the recommendation information to the user according to the order processing path comprises: Performing interface rendering based on the recommendation information, generating an order operation interface and displaying it to the user; The order operation interface includes clickable controls; Accordingly, after the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed, the method further includes: Detecting a click operation performed by the user on the order operation interface; In the case where it is detected that the user submits a confirmation instruction by clicking the clickable control, the recommendation information is triggered and the termination instruction is cancelled; or In the case where the user does not click on the clickable control, the termination instruction is executed.

6. The transaction processing method according to claim 5, before the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is performed, it also includes: Query the historical display record of displaying the order operation interface to the user for the transaction order; If the query result is empty, the step of displaying the order operation interface carrying the recommendation information to the user according to the order processing path is executed.

7. The transaction processing method according to claim 1, wherein displaying the order operation interface carrying the recommendation information to the user according to the order processing path comprises: Determine a component template of a component to be displayed corresponding to the recommendation information; Using the recommendation information as rendering data, rendering the component template, generating an information display component, and displaying it to the user through an information interaction window; The information interaction window includes clickable controls.

8. The transaction processing method according to claim 1, further comprising: Calling a conversation interface to interact with the user, and sending the recommendation information to the user by sending a voice message during the conversation; Receiving voice information and / or key feedback information returned by the user during the conversation; If it is determined according to the voice information and / or the key feedback information that the user confirms to accept the recommendation information, the recommendation information is triggered and the termination instruction is cancelled; or If it is determined according to the voice information and / or the key feedback information that the user refuses to accept the recommendation information, the recommendation information is not triggered and the termination instruction is executed.

9. The transaction processing method according to claim 8, before the step of calling the conversation interface to interact with the user and sending the recommendation information to the user by sending a voice message during the conversation, further comprising: Determining a session interaction time for performing a session interaction with the user; Determining whether the conversation interaction time falls within a preset time interval; If so, query the interaction record of the conversation interaction with the user within a preset time period, and determine whether the interaction record is empty; If the interaction record is empty, the step of calling the conversation interface to interact with the user in a conversation and sending the recommendation information to the user by sending a voice message during the conversation is executed.

10. The transaction processing method according to claim 1, wherein the step of predicting the user's termination intention information based on the operation information comprises: The operation information is input into a pre-trained intention information recognition model to obtain the termination intention information output by the model.

11. The transaction processing method according to claim 10, wherein determining the recommended information and order processing path corresponding to the termination instruction according to the termination intention information comprises: Inputting the termination intention information and the user profile of the user into a pre-trained information matching model, and obtaining a target processing method output by the model that matches the termination intention information; Determine a processing rule of at least one termination instruction in the target processing mode whose probability of being triggered meets a preset probability threshold, and use the processing rule as the recommendation information; And, the information sending method in which the triggering probability of the recommended information is greater than a preset probability threshold is used as the order processing path.

12. A transaction processing device, comprising: A receiving module, configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; A prediction module is configured to predict the termination intention information of the user based on the operation information, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The prediction of the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is obtained by training with the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; a determination module configured to determine, based on the termination intention information, to display an order operation interface carrying recommendation information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface, wherein the termination intention information and the recommendation information have a corresponding relationship, and different termination intention information corresponds to different recommendation information; The determination module includes: a determination sub-module, configured to determine the recommended information and order processing path corresponding to the termination instruction according to the termination intention information; a display sub-module, configured to display an order operation interface carrying the recommended information to the user according to the order processing path, and the order processing path includes an online path or an offline path.

13. A transaction processing method, comprising: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; According to the transaction object information in the transaction order and the termination intention information, determining to display an operation interface carrying a transaction object recommendation list to the user, wherein the termination intention information and the transaction object recommendation list have a corresponding relationship, and different termination intention information corresponds to different transaction object recommendation lists; The determining, based on the transaction object information in the transaction order and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list includes: Determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, and the order processing path includes an online path or an offline path.

14. A transaction processing device, comprising: An instruction receiving module is configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; The information prediction module is configured to predict the termination intention information of the user based on the operation information, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The prediction of the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model, and obtaining the termination intention information output by the model, wherein the intention information recognition model is obtained by training with the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; an information determination module, configured to determine to display an operation interface carrying a transaction object recommendation list to the user according to the transaction object information in the transaction order and the termination intention information, wherein the termination intention information and the transaction object recommendation list have a corresponding relationship, and different termination intention information corresponds to different transaction object recommendation lists; The information determination module is also configured to determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; and display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, wherein the order processing path includes an online path or an offline path.

15. A transaction processing method, comprising: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; Determine, based on the historical transaction data of the user, the attribute data of the user and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list, wherein the termination intention information and the transaction object recommendation list have a corresponding relationship, and different termination intention information corresponds to different transaction object recommendation lists; The determining, based on the historical transaction data of the user, the attribute data of the user, and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list includes: Determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, and the order processing path includes an online path or an offline path.

16. A transaction processing device, comprising: A termination instruction receiving module, configured to receive a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; The intention information prediction module is configured to predict the termination intention information of the user based on the operation information, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The prediction of the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is obtained by training with the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; an intention information determination module, configured to determine, based on the historical transaction data of the user, the attribute data of the user and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list, wherein different termination intention information corresponds to different transaction object recommendation lists; The intention information determination module is also configured to determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; and display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, wherein the order processing path includes an online path or an offline path.

17. An information recommendation method, comprising: Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user; Based on the refund application information, predict the user's refund intention information, wherein the refund application information includes the refund reason, the user's attribute information and the receipt status of the goods, and different refund application information predicts different refund intention information of the user. The method of predicting the user's refund intention information based on the refund application information includes: inputting the refund application information into a pre-trained intention information recognition model to obtain the refund intention information output by the model, wherein the intention information recognition model uses the user's historical terminated order data, the transaction object information contained in the transaction order involved in the user's initiation of the termination instruction, and the user's attribute information as training samples, and uses the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels for training; Based on the refund intention information, determine to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan, wherein the refund intention information and the recommendation information have a corresponding relationship, and different refund intention information corresponds to different recommendation information; The step of determining, based on the refund intention information, to send an order processing solution carrying recommendation information to the client comprises: Determine the recommended information and order processing path corresponding to the refund instruction according to the refund intention information; display the order processing plan carrying the recommended information to the user according to the order processing path, and the order processing path includes an online path or an offline path.

18. According to the information recommendation method of claim 17, the client receives the order processing plan, renders a recommendation page based on the order processing plan, and displays it to the user.

19. An information recommendation device, comprising: An instruction receiving module is configured to receive a refund instruction initiated by a client for a transaction order, wherein the refund instruction includes refund application information input by a user; The identification module is configured to predict the user's refund intention information based on the refund application information, wherein the refund application information includes a refund reason, user attribute information, and a receipt status of the goods, and different refund application information predicts different refund intention information of the user. The method of predicting the user's refund intention information based on the refund application information includes: inputting the refund application information into a pre-trained intention information identification model to obtain the refund intention information output by the model, wherein the intention information identification model is obtained by training with the user's historical terminated order data, the transaction object information contained in the transaction order involved in the user's initiation of the termination instruction, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as a training label; a determination module configured to determine, based on the refund intention information, to send an order processing plan carrying recommendation information to the client, so that the user processes the refund operation of the transaction order according to the order processing plan, wherein the refund intention information and the recommendation information have a corresponding relationship, and different refund intention information corresponds to different recommendation information; The determination module is also configured to determine the recommended information and order processing path corresponding to the refund instruction according to the refund intention information; and display the order processing plan carrying the recommended information to the user according to the order processing path, wherein the order processing path includes an online path or an offline path.

20. An information recommendation method, comprising: Receiving a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund application information input by the user, wherein the refund application information includes a refund reason, attribute information of the user, and receipt status of the product; Sending the refund instruction to a processing platform; Receive the order processing plan with recommendation information returned by the processing platform, render a recommendation page based on the order processing plan and display it to the user, wherein the order processing plan with recommendation information is determined based on refund intention information, and the refund intention information is predicted by inputting the refund application information into the intention information recognition model; the order processing plan with recommendation information is determined according to the refund intention information. The recommended information and the order processing path corresponding to the refund instruction are determined; the order processing plan with recommendation information is displayed to the user according to the order processing path, and the order processing path includes an online path or an offline path; Among them, the intention information recognition model uses the user's historical termination order data, the transaction object information contained in the transaction order involved in the user's termination instruction, and the user attribute information as training samples, and uses the order processing method selected by the user for the transaction order involved in the termination instruction as training labels.

21. An information recommendation device, comprising: A receiving module, configured to receive a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund application information input by the user, wherein the refund application information includes a refund reason, attribute information of the user, and a receipt status of the product; An instruction sending module is configured to send the refund instruction to a processing platform; A page display module is configured to receive an order processing solution carrying recommendation information returned by the processing platform, render a recommendation page based on the order processing solution, and display it to the user, wherein the order processing solution carrying the recommendation information is determined based on refund intention information, and the refund intention information is obtained by inputting the refund application information into an intention information recognition model for prediction; the order processing solution carrying the recommendation information is obtained by determining the recommendation information and the order processing path corresponding to the refund instruction according to the refund intention information; and the order processing solution carrying the recommendation information is displayed to the user according to the order processing path, and the order processing path includes an online path or an offline path; Among them, the intention information recognition model uses the user's historical termination order data, the transaction object information contained in the transaction order involved in the user's termination instruction, and the user attribute information as training samples, and uses the order processing method selected by the user for the transaction order involved in the termination instruction as training labels.

22. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; Based on the termination intention information, determine to display an order operation interface carrying the recommended information to the user, so that the user processes the termination operation of the transaction order according to the order operation interface, wherein the termination intention information and the recommended information have a corresponding relationship, and different termination intention information corresponds to different recommended information; The determining, based on the termination intention information, to display an order operation interface carrying the recommendation information to the user includes: Determine the recommended information and order processing path corresponding to the termination instruction according to the termination intention information; display the order operation interface carrying the recommended information to the user according to the order processing path, and the order processing path includes an online path or an offline path.

23. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; According to the transaction object information in the transaction order and the termination intention information, determining to display an operation interface carrying a transaction object recommendation list to the user, wherein the termination intention information and the recommendation list have a corresponding relationship, and different termination intention information corresponds to different transaction object recommendation lists; The determining, based on the transaction object information in the transaction order and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list includes: Determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, and the order processing path includes an online path or an offline path.

24. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Receiving a termination instruction initiated by a user for a transaction order, wherein the termination instruction includes operation information input by the user; Based on the operation information, predict the termination intention information of the user, wherein the operation information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different operation information predicts different termination intention information of the user. The method of predicting the termination intention information of the user based on the operation information includes: inputting the operation information into a pre-trained intention information recognition model to obtain the termination intention information output by the model, wherein the intention information recognition model is trained using the historical termination order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels; Determine, based on the historical transaction data of the user, the attribute data of the user and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list, wherein the termination intention information and the recommendation list have a corresponding relationship, and different termination intention information corresponds to different transaction object recommendation lists; The determining, based on the historical transaction data of the user, the attribute data of the user, and the termination intention information, to display to the user an operation interface carrying a transaction object recommendation list includes: Determine a transaction object recommendation list and an order processing path corresponding to the termination instruction according to the termination intention information; display an operation interface carrying the transaction object recommendation list to the user according to the order processing path, and the order processing path includes an online path or an offline path.

25. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Receive a refund instruction initiated by the client for the transaction order, wherein the refund instruction includes refund application information input by the user; Identify refund intention information according to the refund application information, wherein the refund application information includes a refund reason, attribute information of the user, and a receipt status of the goods, and different refund application information predicts different refund intention information of the user, and the identifying refund intention information according to the refund application information includes: inputting the refund application information into a pre-trained intention information recognition model, and obtaining the refund intention information output by the model, wherein the intention information recognition model uses the historical terminated order data of the user, the transaction object information contained in the transaction order involved in the initiation of the termination instruction by the user, and the user attribute information as training samples, and uses the order processing method selected by the user for the transaction order involved in the initiation of the termination instruction as training labels for training; Based on the refund intention information, determine to display an order processing plan with recommended information to the user, so that the user processes the refund operation of the transaction order according to the order processing plan, wherein the refund intention information and the recommended information have a corresponding relationship, and different refund intention information corresponds to different recommended information; The step of determining, based on the refund intention information, to send an order processing solution carrying recommendation information to the client comprises: Determine the recommended information and order processing path corresponding to the refund instruction according to the refund intention information; display the order processing plan carrying the recommended information to the user according to the order processing path, and the order processing path includes an online path or an offline path.

26. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions: Receiving a refund instruction initiated by a user for a transaction order, wherein the refund instruction includes refund application information input by the user, wherein the refund application information includes a refund reason, attribute information of the user, and receipt status of the product; Sending the refund instruction to a processing platform; Receive the order processing plan with recommendation information returned by the processing platform, render a recommendation page based on the order processing plan and display it to the user, wherein the order processing plan with recommendation information is determined based on refund intention information, and the refund intention information is predicted by inputting the refund application information into the intention information recognition model; the order processing plan with recommendation information is determined according to the refund intention information. The recommended information and the order processing path corresponding to the refund instruction are determined; the order processing plan with recommendation information is displayed to the user according to the order processing path, and the order processing path includes an online path or an offline path; Among them, the intention information recognition model uses the user's historical termination order data, the transaction object information contained in the transaction order involved in the user's termination instruction, and the user attribute information as training samples, and uses the order processing method selected by the user for the transaction order involved in the termination instruction as training labels.

27. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the transaction processing method according to any one of claims 1 to 11.

28. A computer-readable storage medium storing computer instructions, which implement the steps of the transaction processing method according to claim 13 when executed by a processor.

29. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the transaction processing method of claim 15.

30. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the information recommendation method according to any one of claims 17 to 18.

31. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the information recommendation method of claim 20.

Images