Business processing method, apparatus and electronic device

Abstract

The present invention discloses a service processing method, apparatus, electronic device and computer-readable medium. The method includes: obtaining a first set of variables related to a first channel; obtaining a second set of variables related to a second channel; calculating the common variables between the first set of variables and the second set of variables; extracting historical service input data and historical service processing results that match the common variables from the historical service data processed through the first channel, and training a service processing model; when receiving a request for processing a service by a user through the second channel, extracting service input data that matches the common variables from the service data corresponding to the second channel, and using the service processing model to process the service input data to obtain a service processing result. According to the present invention, it is allowed to train a model using historical service data corresponding to one channel, so as to process a service handling request under another channel, and it is not necessary to have sufficient historical data under the other channel for model training.

Description

Technical Field

[0001] The present invention relates to the field of computer information processing, and in particular, to a service processing method, device, electronic device, and computer-readable medium. Background Art

[0002] Currently, for various Internet services, it is usually necessary to use a service processing model to process requests for users to handle services and output processing results for users. Before using the service processing model for service processing, it is necessary to train the service processing model, and a large amount of historical service data is required for training the model.

[0003] Since there are different channels for handling the same service, the service data required to be input by users varies among different channels. Often, there is more historical service data accumulated under some channels, which can be used to train the service model, while there is less historical service data accumulated under other channels, making it difficult to train a service processing model with high quality, and thus difficult to effectively process service requests made by users through these channels.

[0004] Therefore, a new technical solution is needed that can train an effective service processing model for a certain channel when the historical service data corresponding to the channel is insufficient, so as to process services for users. Summary of the Invention

[0005] The present invention aims to train an effective service processing model for a certain channel when the historical service data corresponding to the channel is insufficient, so as to process services for users.

[0006] To solve the above technical problems, a first aspect of the present invention provides a service processing method, including: obtaining a first set of variables related to a first channel; obtaining a second set of variables related to a second channel; calculating common variables between the first set of variables and the second set of variables; extracting historical service input data and historical service processing results that match the common variables from historical service data processed through the first channel, and using the historical service input data and the historical service processing results to train a service processing model; when receiving a request for a user to handle a service through the second channel, extracting service input data that matches the common variables from the service data corresponding to the second channel, and using the service processing model to process the service input data to obtain a service processing result.

[0007] According to a preferred embodiment of the present invention, calculating the common variables of the first set of variables and the second set of variables includes: constructing a source domain based on the first set of variables and constructing a target domain based on the second set of variables; calculating a transformation factor based on a joint distribution adaptation method, the transformation factor making the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold; using the transformation factor to convert the first set of variables or the second set of variables into the common variables.

[0008] According to a preferred embodiment of the present invention, obtaining the first set of variables related to the first channel includes: screening the variables related to the first channel according to the importance or information value to obtain the first set of variables.

[0009] According to a preferred embodiment of the present invention, obtaining the second set of variables related to the second channel includes: when the variables related to the second channel are lower than a preset second threshold, querying other variables associated with the variables related to the second channel; screening the variables related to the second channel and other variables associated with them according to the importance or information value to obtain the second set of variables.

[0010] According to a preferred embodiment of the present invention, querying other variables associated with the variables related to the second channel includes: querying a third channel, the services processed by the third channel and the services processed by the second channel having common service characteristics; querying the other variables from the variables related to the third channel.

[0011] According to a preferred embodiment of the present invention, querying other variables associated with the variables related to the second channel includes: according to the identity information of the user, querying a fourth channel used by the user for historical services already handled; querying the other variables from the variables related to the third channel.

[0012] To solve the above technical problems, a second aspect of the present invention provides a service processing device, including: a first variable acquisition module for acquiring a first set of variables related to a first channel; a second variable acquisition module for acquiring a second set of variables related to a second channel; a common variable calculation module for calculating the common variables between the first set of variables and the second set of variables; a model training module for extracting historical service input data and historical service processing results that match the common variables from the historical service data processed through the first channel, and using the historical service input data and the historical service processing results to train a service processing model; and a service processing module for, when receiving a request from a user to process a service through the second channel, extracting service input data that matches the common variables from the service data corresponding to the second channel, and using the service processing model to process the service input data to obtain a service processing result.

[0013] According to a preferred embodiment of the present invention, the common variable calculation module includes: a source domain construction module for constructing a source domain based on the first set of variables; a target domain construction module for constructing a target domain based on the second set of variables; a transformation factor calculation module for calculating a transformation factor based on a joint distribution adaptation method, the transformation factor making the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold; and a common variable conversion module for using the transformation factor to convert the first set of variables or the second set of variables into the common variables.

[0014] According to a preferred embodiment of the present invention, the first variable acquisition module screens the variables related to the first channel according to the importance or information value, and obtains the first set of variables.

[0015] According to a preferred embodiment of the present invention, when the variables related to the second channel are lower than a preset second threshold, the second variable acquisition module queries other variables that are associated with the variables related to the second channel; and screens the variables related to the second channel and the other variables associated therewith according to the importance or information value to obtain the second set of variables.

[0016] According to a preferred embodiment of the present invention, the second variable acquisition module queries a third channel, and the services processed through the third channel and the services processed through the second channel have common service characteristics; and queries the other variables from the variables related to the third channel.

[0017] According to a preferred embodiment of the present invention, the second variable acquisition module queries a fourth channel used by the user to handle historical services according to the identity information of the user; and queries the other variables from the variables related to the third channel.

[0018] To solve the above technical problems, a third aspect of the present invention provides an electronic device, which includes a processor and a memory storing computer-executable instructions. When the computer-executable instructions are executed, the processor performs the above method.

[0019] To solve the above technical problems, a fourth aspect of the present invention provides a computer-readable storage medium storing one or more programs. When the one or more programs are executed by a processor, the above method is implemented.

[0020] According to the technical solution of the present invention, users can handle the same business through different channels. The channel variables define the types of data that need to be input when users handle business. Different channels have different variables, that is, users are required to input different business data. When two channels have common variables, it means that there is a common part between the business data used by the two channels. Based on this common variable, historical business data under one channel can be screened and then a business model can be trained. Then, when a user needs to handle business through another channel, the business data input by the user is filtered according to this common variable. Since the filtered business data and the training model both match the common variable, the filtered business data can be processed by this model to obtain a business processing result. It can be seen that the present invention allows using historical business data corresponding to one channel to train a model, so as to process a business handling request under another channel, and it is not necessary to have sufficient historical data under another channel for model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to make the technical problems solved by the present invention, the technical means adopted, and the technical effects achieved more clear, the specific embodiments of the present invention will be described in detail below with reference to the drawings. However, it should be noted that the drawings described below are only the drawings of the exemplary embodiments of the present invention. For those skilled in the art, other drawings of embodiments can be obtained based on these drawings without creative efforts.

[0022] Figure 1 is a flowchart of a business processing method according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of a business processing method according to an embodiment of the present invention;

[0024] Figure 3 is a flowchart of a business processing method according to an embodiment of the present invention;

[0025] Figure 4 is a flowchart of a business processing method according to an embodiment of the present invention;

[0026] Figure 5It is a block diagram of a service processing device according to an embodiment of the present invention;

[0027] Figure 6 It is a block diagram of a service processing device according to an embodiment of the present invention;

[0028] Figure 7 It is a block diagram of an electronic device according to an embodiment of the present invention;

[0029] Figure 8 It is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. Detailed implementation manners

[0030] Now, exemplary embodiments of the present invention will be described more fully with reference to the accompanying drawings. Although the exemplary embodiments can be implemented in many specific ways, it should not be understood that the present invention is limited to the embodiments described herein. On the contrary, these exemplary embodiments are provided to make the content of the present invention more complete and to more conveniently convey the inventive concept to those skilled in the art.

[0031] On the premise of conforming to the technical concept of the present invention, the structures, performances, effects or other features described in a specific embodiment can be combined with one or more other embodiments in any suitable manner.

[0032] In the process of introducing specific embodiments, the detailed descriptions of the structures, performances, effects or other features are for those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can implement the present invention with technical solutions that do not contain the above-mentioned structures, performances, effects or other features under specific circumstances.

[0033] The flowcharts in the accompanying drawings are only exemplary flow demonstrations, and do not mean that all the contents, operations and steps in the flowcharts must be included in the solutions of the present invention, nor does it mean that they must be executed in the order shown in the figures. For example, some operations / steps in the flowchart can be decomposed, some operations / steps can be combined or partially combined, etc. Without departing from the gist of the present invention, the execution order shown in the flowchart can be changed according to the actual situation.

[0034] The blocks in the accompanying drawings Figure 1 generally represent functional entities, and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0035] In the accompanying drawings, the same reference numerals denote the same or similar elements, components, or parts, and thus the repeated description of the same or similar elements, components, or parts may be omitted hereinafter. It should also be understood that although the first, second, third, etc. attributives indicating numbers may be used herein to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these attributives. That is to say, these attributives are only used to distinguish one from another. For example, the first device may also be called the second device without departing from the essential technical solution of the present invention. In addition, the terms "and / or", "or / and" mean all combinations including any one or more of the items listed.

[0036] In the field of the Internet, the same service provides different handling channels for users. For example, when a user wants to shop online, different applications and web pages provide corresponding channels, and these channels have different variables, that is, users are required to input different types of service data, such as name, mobile phone number, social account, payment account, and so on. In the present invention, a first set of variables related to a first channel and a second set of variables related to a second channel are obtained, and the common variables between the first set of variables and the second set of variables are calculated. When the two channels have common variables, it indicates that there is a common part between the service data used by the two channels, such as name, mobile phone number, etc. Historical service input data and historical service processing results that match the common variables are extracted from the historical service data processed through the first channel, and the service processing model is trained using the historical service input data and historical service processing results; when a request for processing a service by the user through the second channel is received, service input data that matches the common variables is extracted from the service data corresponding to the second channel. Since both the training model and the service input data match the common variables, the service input data is processed using the service processing model to obtain a service processing result. It can be seen that the present invention allows a historical service data corresponding to one channel to be used to train the model, so as to process a service handling request under another channel, and it is not necessary to have sufficient historical data under the other channel for model training.

[0037] As Figure 1 shown, in an embodiment of the present invention, a service processing method is proposed, including:

[0038] Step S110, obtaining a first set of variables related to a first channel.

[0039] Step S120, obtaining a second set of variables related to a second channel.

[0040] In this embodiment, users need to handle different services through different channels. The channel variables limit the types of service data input by users, and the variables used in different channels are also different. For example, users can apply for an Internet loan through the channel provided by Application A or through the channel provided by Application B. The variables corresponding to the Application A channel include name, occupation, assets, etc., and the variables corresponding to Application B include name, work unit, house, vehicle, etc. It can be seen that the variables of the Application A channel and the Application B channel are different.

[0041] Step S130: Calculate the common variables between the first set of variables and the second set of variables.

[0042] In this embodiment, as Figure 2 shown, calculate the common variables between the first set of variables and the second set of variables. The existence of common variables indicates that there is a common part between the service data used by the first channel and the second channel. For example, both the Application A channel and the Application B channel require the input of name, and the asset information of the Application A channel is similar to the vehicle and house information of the Application B channel.

[0043] Step S140: Extract the historical service input data and historical service processing results that match the common variables from the historical service data processed through the first channel, and use the historical service input data and historical service processing results to train the service processing model.

[0044] Step S150: When receiving a request for the user to handle a service through the second channel, extract the service input data that matches the common variables from the service data corresponding to the second channel, and use the service processing model to process the service input data to obtain the service processing result.

[0045] According to the technical solution of the present invention, based on the common variables, the historical service data under the first channel can be screened and then the service model can be trained. When the user needs to handle a service through the second channel, the service data input by the user can be filtered according to the common variables. Since the filtered service data and the training model both match the common variables, the service processing result can be obtained by processing the filtered service data through the model. That is, the present invention does not require sufficient historical data under the second channel for model training, and can process the service handling request under the second channel.

[0046] As Figure 3As shown, according to the foregoing embodiments, step S130 can be implemented by using a feature-based transfer learning method. The principle of this method is as follows: mutual transfer is performed through feature transformation to reduce the gap between the source domain and the target domain; or the data features of the source domain and the target domain are transformed into a unified feature space, and then traditional machine learning methods are used for classification and recognition. Specifically, step S130 includes:

[0047] Step S1310, constructing a source domain based on a first set of variables and constructing a target domain based on a second set of variables.

[0048] Step S1320, calculating a transformation factor based on a joint distribution adaptation method, where the transformation factor makes the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold.

[0049] In this embodiment, the magnitude of the first threshold is not limited. In this embodiment, the joint distribution adaptation method (JDA) is a probability distribution adaptation method, and what is adapted is the joint probability. For a random variable X, x ∈ X is its element, and for each element, there corresponds a category y ∈ Y. Then, its marginal probability is P(X), the conditional probability is P(y│X), and the joint probability is p(X,y). The JDA method is to adapt the joint probability of the source domain and the target domain, that is, to find a transformation factor A such that the distances of P(A T X s ) and P(A T X t ) can be as close as possible. At the same time, the distances of P(Y s |A T X s ) and P(Y t |A T X t ) are also small. Finally, the optimization objective is:

[0050]

[0051] Where: is a regularization term.

[0052] Step S1330, using the transformation factor to convert the first set of variables or the second set of variables into common variables.

[0053] According to the technical solution of this embodiment, after obtaining the transformation factor A, the first set of variables or the second set of variables can be converted by the transformation factor A to obtain common variables.

[0054] For example Figure 4As shown in the figure, in one embodiment of the present invention, a service processing method is proposed, including:

[0055] Step S410: Screen the variables related to the first channel according to the importance or information value, and obtain the first set of variables.

[0056] In this embodiment, generally, the higher the importance or information value of a variable, the greater its value in business processing. Specifically, for the channels provided by Application A, select the m-dimensional variables with higher importance or iv (information value) from all the variables of this channel as the source domain X.

[0057] Step S420: When the variables related to the second channel are lower than the preset second threshold, query other variables associated with the variables related to the second channel.

[0058] Step S430: Screen the variables related to the second channel and other variables associated with them according to the importance or information value, and obtain the second set of variables.

[0059] In this embodiment, for example, when the number of variables of the channel provided by Application B is small, it is difficult to calculate the common variables. At this time, it is necessary to perform brute-force attacks based on the variables of the Application B channel to discover other relevant variables. After summarization, select the m-dimensional variables with higher importance or iv (information value) as the target domain X. It should be noted that both the target domain X and the source domain X are structured data, but only a part of the variables are the same fields, and the selected variable dimensions are the same and are all m.

[0060] In this embodiment, two methods are provided for discovering the relevant variables of the second-channel variables:

[0061] (1) Query the third channel. The services processed through the third channel and the services processed through the second channel have common service characteristics. Query other variables from the variables related to the third channel.

[0062] In this embodiment, the services corresponding to the third channel and the services corresponding to the second channel have common service characteristics, indicating that the services processed through the third channel are the same or similar to the services processed through the second channel. Then, the variables corresponding to the third channel and the variables corresponding to the second channel may be partially the same, and other valuable variables can be associated based on the same part.

[0063] (2) According to the user's identity information, query the fourth channel used by the user for the historical services already processed; query other variables from the variables related to the third channel.

[0064] In this embodiment, the fourth channel for querying the historical business handled by the user according to the user identity is determined. When the businesses handled by the same user are the same or similar, some of the variables corresponding to the fourth channel may be the same as those corresponding to the second channel. Based on the same part, other valuable variables can be associated.

[0065] Step S440: Calculate the common variables between the first set of variables and the second set of variables.

[0066] Step S450: Extract the historical business input data and historical business processing results that match the common variables from the historical business data processed through the first channel, and use the historical business input data and historical business processing results to train the business processing model.

[0067] Step S460: When receiving a request for the user to handle a business through the second channel, extract the business input data that matches the common variables from the business data corresponding to the second channel, and use the business processing model to process the business input data to obtain the business processing result.

[0068] According to the technical solution of this embodiment, the transformation factor is calculated using the JDA method, and dimensionality transformation is achieved through the transformation factor. The source domain X and the target X are reduced to n dimensions to obtain the common variables. Based on the common variables, the business processing model is trained on the source domain samples (historical data of the first channel), and tested on the target domain samples (data used for processing the second channel business during the model training process). Through multiple iterative optimization calculations, the obtained model can be used to effectively process business requests from the second channel.

[0069] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments are implemented as a program executed by a data processing device (including a computer), that is, a computer program. When this computer program is executed, the above method provided by the present invention can be implemented. Moreover, the computer program can be stored in a computer-readable storage medium, and this storage medium can be a readable storage medium such as a disk, an optical disc, a ROM, a RAM, etc., or a storage array composed of multiple storage media, such as a disk or tape storage array. The storage medium is not limited to centralized storage, and it can also be distributed storage, such as cloud storage based on cloud computing.

[0070] Next, the device embodiments of the present invention will be described. This device can be used to execute the method embodiments of the present invention. For the details described in the device embodiments of the present invention, they should be regarded as a supplement to the above method embodiments; for the details not disclosed in the device embodiments of the present invention, they can be implemented with reference to the above method embodiments.

[0071] As Figure 5 shown, in an embodiment of the present invention, a business processing device is proposed, including:

[0072] The first variable acquisition module 510 acquires a first set of variables related to the first channel.

[0073] The second variable acquisition module 520 acquires a second set of variables related to the second channel.

[0074] In this embodiment, the user needs to handle different services through different channels. The channel variables limit the types of service data input by the user, and the variables used by different channels are also different. For example, the user can apply for an Internet loan through the channel provided by Application A or through the channel provided by Application B. The variables corresponding to the Application A channel include name, occupation, assets, etc., and the variables corresponding to Application B include name, work unit, house, vehicle, etc. It can be seen that the variables of the Application A channel and the Application B channel are different.

[0075] The common variable calculation module 530 calculates the common variables between the first set of variables and the second set of variables.

[0076] In this embodiment, as Figure 2 shown, the common variables between the first set of variables and the second set of variables are calculated. The existence of the common variables indicates that there is a common part between the service data used by the first channel and the second channel. For example, both the Application A channel and the Application B channel require the input of the name, and the asset information of the Application A channel is similar to the vehicle and house information of the Application B channel.

[0077] The model training module 540 extracts the historical service input data and historical service processing results that match the common variables from the historical service data processed through the first channel, and uses the historical service input data and historical service processing results to train the service processing model.

[0078] The service processing module 550, when receiving a request for the user to handle a service through the second channel, extracts the service input data that matches the common variables from the service data corresponding to the second channel, and uses the service processing model to process the service input data to obtain the service processing result.

[0079] According to the technical solution of the present invention, based on the common variables, the historical service data under the first channel can be screened and then the service model can be trained. When the user needs to handle a service through the second channel, the service data input by the user can be filtered according to the common variables. Since the filtered service data and the training model both match the common variables, the service processing result can be obtained by processing the filtered service data through the model. That is, the present invention does not require sufficient historical data under the second channel for model training, and can process the service handling request under the second channel.

[0080] As Figure 6As shown, according to the foregoing embodiments, the common variable calculation module 530 may be implemented by using a feature-based transfer learning method. The principle of this method is as follows: mutual transfer is performed through feature transformation to reduce the gap between the source domain and the target domain; or the data features of the source domain and the target domain are transformed into a unified feature space, and then traditional machine learning methods are used for classification and recognition. Specifically, the common variable calculation module 530 includes:

[0081] A source domain construction module 5310 that constructs a source domain based on a first set of variables;

[0082] A target domain construction module 5320 that constructs a target domain based on a second set of variables.

[0083] A transformation factor calculation module 5330 that calculates a transformation factor based on a joint distribution adaptation method, and the transformation factor makes the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold.

[0084] In this embodiment, the size of the first threshold is not limited. In this embodiment, the joint distribution adaptation method (JDA) is a probability distribution adaptation method, and what is adapted is the joint probability. For a random variable X, x ∈ X is its element, and for each element, there corresponds a category y ∈ Y. Then, its marginal probability is P(X), the conditional probability is P(y│X), and the joint probability is p(X,y). The JDA method is to adapt the joint probability of the source domain and the target domain, that is, to find a transformation factor A such that the distances between P(A T X s ) and P(A T X t ) can be as close as possible. At the same time, the distances between P(Y s |A T X s ) and P(Y t |A T X t ) are also small. Finally, the optimization objective:

[0085]

[0086] Where: is a regularization term.

[0087] A common variable conversion module 5340 that uses the transformation factor to convert the first set of variables or the second set of variables into common variables.

[0088] According to the technical solution of this embodiment, after obtaining the transformation factor A, the first set of variables or the second set of variables can be transformed by the transformation factor A to obtain the common variable.

[0089] As Figure 5 shown, in an embodiment of the present invention, a service processing device is proposed, including:

[0090] The first variable acquisition module 510 screens the variables related to the first channel according to the importance or the level of information value to obtain the first set of variables.

[0091] In this embodiment, generally, the higher the importance or information value of the variable, the greater its value in business processing. Specifically, for the channel provided by the A application, m-dimensional variables with higher importance or iv (information value) are selected from all the variables of this channel as the source domain X.

[0092] The second variable acquisition module 520 queries other variables associated with the variables related to the second channel when the variables related to the second channel are lower than the preset second threshold, and screens the variables related to the second channel and other variables associated with it according to the importance or the level of information value to obtain the second set of variables.

[0093] In this embodiment, for example, when the number of variables in the channel provided by the B application is small, it is difficult to calculate the common variable. At this time, it is necessary to perform multi-head brute force matching based on the variables of the B application channel to find other relevant variables. After summarization, m-dimensional variables with higher importance or iv (information value) are selected as the target domain X. It should be noted that both the target domain X and the source domain X are structured data, but only a part of the variables are the same fields, and the selected variable dimensions need to be the same and are all m.

[0094] In this embodiment, two methods are provided for discovering the relevant variables of the second channel variables:

[0095] (1) Query the third channel. The services processed through the third channel and the services processed through the second channel have common service characteristics, and other variables are queried from the variables related to the third channel.

[0096] In this embodiment, the services corresponding to the third channel and the services corresponding to the second channel have common service characteristics, indicating that the services processed through the third channel are the same or similar to the services processed through the second channel. Then, the variables corresponding to the third channel and the variables corresponding to the second channel may be partially the same, and other valuable variables can be associated based on the same part.

[0097] (2) Query the fourth channel used by the user for the historical services already processed according to the user's identity information; query other variables from the variables related to the third channel.

[0098] In this embodiment, the fourth channel for querying the historical business handled by the user according to the user identity is determined. When the businesses handled by the same user are the same or similar, some of the variables corresponding to the fourth channel may be the same as those corresponding to the second channel. Based on the same part, other valuable variables can be associated.

[0099] The common variable calculation module 530 calculates the common variables between the first set of variables and the second set of variables.

[0100] The model training module 540 extracts the historical business input data and historical business processing results that match the common variables from the historical business data processed through the first channel, and uses the historical business input data and historical business processing results to train the business processing model.

[0101] When receiving a request for the user to handle a business through the second channel, the business processing module 550 extracts the business input data that matches the common variables from the business data corresponding to the second channel, and uses the business processing model to process the business input data to obtain the business processing result.

[0102] According to the technical solution of this embodiment, the transformation factor is calculated using the JDA method, and dimensionality transformation is achieved through the transformation factor. The source domain X and the target X are reduced to n dimensions to obtain the common variables. Based on the common variables, the business processing model is trained on the source domain samples (historical data of the first channel), and tested on the target domain samples (data used for processing the second channel business during the model training process). Through multiple iterative optimization calculations, the obtained model can be used to effectively process business requests from the second channel.

[0103] Those skilled in the art can understand that the various modules in the above device embodiments can be distributed in the device as described, or can be correspondingly changed and distributed in one or more devices different from the above embodiments. The modules in the above embodiments can be combined into one module, or further split into multiple sub-modules.

[0104] Next, an embodiment of the electronic device of the present invention is described. This electronic device can be regarded as an implementation form of the entity of the above method and device embodiments of the present invention. For the details described in the embodiment of the electronic device of the present invention, they should be regarded as a supplement to the above method or device embodiments; for the details not disclosed in the embodiment of the electronic device of the present invention, they can be implemented with reference to the above method or device embodiments.

[0105] Figure 7 It is a structural block diagram of an exemplary embodiment of an electronic device according to the present invention. Figure 7 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0106] AsFigure 7 As shown, the electronic device 200 of this exemplary embodiment is presented in the form of a general-purpose data processing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components (including the storage unit 220 and the processing unit 210), a display unit 240, etc.

[0107] Among them, the storage unit 220 stores a computer-readable program, which may be the source program or the code of a read-only program. The program can be executed by the processing unit 210, so that the processing unit 210 executes the steps of various embodiments of the present invention. For example, the processing unit 210 can execute steps such as Figure 1 , Figure 3 and Figure 4 as shown.

[0108] The storage unit 220 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 2201 and / or a cache storage unit 2202, and may further include a read-only storage unit (ROM) 2203. The storage unit 220 may also include a program / utilities 2204 having a set (at least one) of program modules 2205. Such program modules 2205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0109] The bus 230 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0110] The electronic device 200 can also communicate with one or more external devices 300 (such as a keyboard, a display, a network device, a Bluetooth device, etc.), enabling a user to interact with the electronic device 200 via these external devices 300, and / or enabling the electronic device 200 to communicate with one or more other data processing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 250, and can also be through the network adapter 260 with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet). The network adapter 260 can communicate with other modules of the electronic device 200 through the bus 230. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0111] Figure 8 is a schematic diagram of an embodiment of a computer-readable medium of the present invention. As Figure 8 shown, the computer program can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. When the computer program is executed by one or more data processing devices, the computer-readable medium can implement the above method of the present invention, that is: obtaining a first set of variables related to a first channel; obtaining a second set of variables related to a second channel; calculating the common variables of the first set of variables and the second set of variables; extracting historical service input data and historical service processing results that match the common variables from the historical service data processed through the first channel, and using the historical service input data and historical service processing results to train a service processing model; when receiving a request from a user to process a service through the second channel, extracting service input data that matches the common variables from the service data corresponding to the second channel, and using the service processing model to process the service input data to obtain a service processing result.

[0112] Based on the descriptions of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described in the present invention can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a data processing device (such as a personal computer, a server, or a network device, etc.) to execute the above method according to the present invention.

[0113] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program used by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0114] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0115] In summary, the present invention can be implemented by a method, apparatus, electronic device, or computer-readable medium that can execute a computer program. Some or all of the functions of the present invention can be implemented by using a general-purpose data processing device such as a microprocessor or a digital signal processor (DSP) in practice.

[0116] In the specific embodiments described above, the object, technical solution and beneficial effects of the present invention have been further described in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general-purpose devices can also implement the present invention. The above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A service processing method, characterized in that Including: Users handle the same business through different channels, and some variables used by different channels are different; Obtain the first set of variables related to the first channel; Obtain the second set of variables related to the second channel; Mutually migrate through data feature transformation to reduce the gap between the source domain and the target domain, or transform the data features of the source domain and the target domain into a unified feature space, and calculate the common variables of the first set of variables and the second set of variables. The common variables indicate that there is a common part between the business data used by the first channel and the second channel, including: constructing a source domain based on the first set of variables, including: using the m-dimensional variables with high importance or information value as the source domain; constructing a target domain based on the second set of variables, including: using the m-dimensional variables with high importance or information value as the target domain; adapting the joint probability of the source domain and the target domain based on the joint distribution adaptation algorithm, and calculating the transformation factor; when the transformation factor makes the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold, use the transformation factor to convert the first set of variables or the second set of variables into common variables, or, perform dimensionality transformation through the transformation factor to reduce the source domain and the target domain to n dimensions to obtain common variables; Extract the historical business input data and historical business processing results that match the common variables from the historical business data processed through the first channel; screen the historical business input data under the first channel based on the common variables and then use the historical business input data and historical business processing results to train the business processing model, or train the business processing model based on the common variables on the historical business data of the first channel, and test the historical business data used when processing the second channel business and perform multiple iterative optimization calculations to obtain the business processing model; When receiving a request from a user to handle a business through the second channel, extract the business input data that matches the common variables from the business data corresponding to the second channel, and use the business processing model that matches the common variables to process the business input data to obtain the business processing result.

2. The service processing method according to claim 1, characterized in that The obtaining of the first set of variables related to the first channel includes: Screen all variables related to the first channel according to the level of importance or information value to obtain the first set of variables.

3. The service processing method according to claim 1, wherein The obtaining of the second set of variables related to the second channel includes: When the variables related to the second channel are lower than a preset second threshold, query other variables that are associated with the variables related to the second channel; Screen the variables related to the second channel and other variables associated with them according to the level of importance or information value to obtain the second set of variables.

4. The service processing method according to claim 3, wherein The querying of other variables that are associated with the variables related to the second channel includes: Query the third channel, and the business processed through the third channel has common business characteristics with the business processed through the second channel; Query other variables from the variables related to the third channel.

5. The service processing method according to claim 4, wherein The querying of other variables that are associated with the variables related to the second channel includes: According to the user's identity information, query the fourth channel used by the user to handle historical business; Query other variables from the variables related to the third channel.

6. A service processing device, characterized in that, Including: The first variable acquisition module, which acquires the first set of variables related to the first channel; A second variable acquisition module that acquires a second set of variables related to a second channel; Among them, when a user handles the same service through different channels, some variables used by different channels are different; A common variable calculation module that calculates the common variables of the first set of variables and the second set of variables by migrating each other through data feature transformation to reduce the gap between the source domain and the target domain, or transforming the data features of the source domain and the target domain into a unified feature space. The common variables indicate that there is a common part between the service data used by the first channel and the second channel, specifically including: A source domain construction module that constructs a source domain based on the first set of variables and uses the m-dimensional variables with high importance or information value as the source domain; A target domain construction module that constructs a target domain based on the second set of variables and uses the m-dimensional variables with high importance or information value as the target domain; A transformation factor calculation module that adapts the joint probability of the source domain and the target domain based on the joint distribution adaptation algorithm and calculates the transformation factor; A common variable conversion module that, when the transformation factor makes the marginal distribution distance and the conditional distribution distance between the source domain and the target domain lower than a preset first threshold, uses the transformation factor to convert the first set of variables or the second set of variables into common variables, or reduces the source domain and the target domain to n dimensions through the transformation factor to obtain common variables; A model training module that extracts historical service input data and historical service processing results matching the common variables from the historical service data processed through the first channel, screens the historical service input data under the first channel based on the common variables, uses the historical service input data and the historical service processing results to train a service processing model, or trains a service processing model based on the common variables on the historical service data of the first channel, tests the historical service data used when processing the service of the second channel, and obtains a service processing model after multiple iterative optimization calculations; A service processing module that, when receiving a request from a user to process a service through the second channel, extracts service input data matching the common variables from the service data corresponding to the second channel, and uses the service processing model matching the common variables to process the service input data to obtain a service processing result.

7. The service processing device according to claim 6, wherein The first variable acquisition module includes: screening the variables related to the first channel according to the importance or information value to obtain a first set of variables.

8. The service processing device according to claim 6, characterized in that The second variable acquisition module includes: when the variables related to the second channel are lower than a preset second threshold, querying other variables associated with the variables related to the second channel; screening the variables related to the second channel and other variables associated with them according to the importance or information value to obtain a second set of variables.

9. The service processing device according to claim 8, wherein The second variable acquisition module further includes: querying a third channel, where the service processed through the third channel has common service characteristics with the service processed through the second channel; querying other variables from the variables related to the third channel.

10. The service processing device according to claim 8, wherein The second variable acquisition module further includes: querying a fourth channel used by the user to handle historical services according to the user's identity information; querying other variables from the variables related to the third channel.

11. An electronic device, including: A processor; and a memory storing computer-executable instructions that, when executed, cause the processor to perform the method according to any one of claims 1-5.

12. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method according to any one of claims 1-5.

Images