Target object matching method, device, storage medium and electronic device

Abstract

The present application discloses a method, device, storage medium and electronic device for matching target objects. The method includes: obtaining first information of each first object in a first set under multiple different first dimensions; obtaining second information of each second object in a second set under multiple different second dimensions; constructing a multi-task deep learning model based on the first information and the second information, obtaining first target information of each first target object in the first target object set under multiple different first dimensions; inputting the first target information into the multi-task deep learning model to obtain the scores corresponding to each first target object; assigning each first target object to the second target object in the second target object set based on the score. The present application solves the technical problem of low recommendation success rate in related technologies due to the inability of historical usage records and business rules to pay attention to the real demands of users.

Description

Technical Field

[0001] The present application relates to the technical field of business recommendation, and in particular to a method, device, storage medium and electronic device for matching a target object. Background Art

[0002] Many industries are faced with the situation where the number of users is much higher than the number of customer service personnel, and user service priorities need to be defined. Due to the many personalized needs of users, the service priorities of customer service personnel need to be constrained by clear rules. In each service link, due to the wide variety of business types, complex business logic, and differences in customer service personnel skills, there will be large deviations in actual user understanding, resulting in the recommendation success rate failing to meet expectations.

[0003] The principle of the recommendation system in related technologies is mainly to compare user historical usage records and business rules. This method can only solve the problem of business recommendations meeting user historical usage needs, but cannot focus on the user's real demands, and therefore cannot fundamentally improve the level of understanding of users.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a target object matching method, device, storage medium and electronic device to at least solve the technical problem in the related art that the recommendation success rate is low due to the historical usage records and business rules that cannot pay attention to the real demands of users.

[0006] According to one aspect of an embodiment of the present application, a method for matching target objects is provided, which is applied in a multi-customer service scenario, including: obtaining first information of each first object in a first set under multiple different first dimensions; obtaining second information of each second object in a second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object; constructing a multi-task deep learning model based on the first information and the second information, and obtaining first target information of each first target object in the first target object set under multiple different first dimensions; inputting the first target information into the multi-task deep learning model to obtain a score corresponding to each first target object; and assigning each first target object to a second target object in the second target object set based on the score, wherein a preset association relationship exists between the second target object and the first target object.

[0007] Optionally, each first target object is assigned to a second target object in a set of second target objects based on the score, including: determining the priority of the first target object according to the score corresponding to each first target object, wherein the higher the priority, the greater the success rate of the second target object to reach a transaction with the first target object; obtaining the business indicator corresponding to each second target object in the set of second target objects, wherein the larger the business indicator, the stronger the business capability of the second target object; and assigning each first target object to the second target object in the set of second target objects according to the business indicator and the priority.

[0008] Optionally, the priority of the first target object is determined according to the score corresponding to each first target object, including: sorting the score corresponding to each first target object based on a predetermined size order to obtain a first sorting result; dividing the first target object into multiple groups of first subsets based on a preset interval and the first sorting result, wherein the priority of each subset in the multiple groups of first subsets is different; and determining the priority of the first subset to which each first target object belongs as the priority corresponding to the first target object.

[0009] Optionally, each first target object is assigned to a second target object in a second target object set according to business indicators and priorities, including: determining a first group number corresponding to multiple groups of subsets; and assigning each first target object to a second target object in a second target object set according to the first group number and business indicators.

[0010] Optionally, each first target object is assigned to a second target object in a second target object set according to the first group number and the business indicator, including: sorting the business indicators based on a predetermined size order to obtain a second sorting result; grouping each second target object in the second target object set into multiple second subsets based on the first group number; and allocating the first subset to the second subset, wherein the greater the business indicator to which the subset belongs, the higher the priority of the first subset allocated to the second subset.

[0011] Optionally, assigning each first target object to a second target object in a second target object set based on the score includes: dividing each first target object in the first target object set according to the size of the score corresponding to each first target object to obtain a division result, wherein the division result at least includes: low-scoring objects and high-scoring objects, wherein the recommendation success rate of the low-scoring objects is lower than the recommendation success rate of the high-scoring objects; combining the high-scoring objects with the low-scoring objects in a predetermined ratio to obtain a combined set to be assigned; and matching the set to be assigned to any second target object in the second target object set.

[0012] Optionally, a multi-task deep learning model is constructed based on the first information and the second information, including: encoding the first information and the second information respectively to obtain first encoded data and second encoded data; receiving input annotation results, and constructing a multi-task learning model based on the first encoded data, the second encoded data and the annotation results.

[0013] Optionally, first information of each first object in the first set under multiple different first dimensions is obtained, including: determining a first identifier corresponding to each first object; calling a language processing algorithm to standardize data information corresponding to the first identifier to obtain data information with a table structure, and determining that the data information with the table structure is the first information; second information of each second object in the second set under multiple different second dimensions is obtained, including: determining a second identifier corresponding to each second object; calling a language processing algorithm to standardize data information corresponding to the second identifier to obtain data information with a table structure, and determining that the data information with the table structure is the second information.

[0014] According to another aspect of an embodiment of the present application, a target object matching device is also provided, which is applied in a multi-customer service scenario, and includes: a first acquisition module, used to obtain first information of each first object in a first set under multiple different first dimensions; a second acquisition module, used to obtain second information of each second object in a second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object; a construction module, used to construct a multi-task deep learning model according to the first information and the second information, and obtain first target information of each first target object in the first target object set under multiple different first dimensions; an input module, used to input the first target information into the multi-task deep learning model, and obtain the score corresponding to each first target object; an allocation module, used to allocate each first target object to a second target object in the second target object set based on the score, wherein a preset association relationship exists between the second target object and the first target object.

[0015] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any target object matching method.

[0016] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any target object matching method.

[0017] In an embodiment of the present application, effective key information extraction is adopted for user data and multi-customer service personnel data to effectively expand the data scope understood by users, by obtaining the first information of each first object in the first set under multiple different first dimensions; obtaining the second message of each second object in the second set under multiple different second dimensions, wherein the first object and the second object have a preset association relationship; constructing a multi-task deep learning model based on the first information and the second information, and obtaining the first target information of each first target object in the first target object set under multiple different first dimensions; inputting the first target information into the multi-task deep learning model to obtain the score corresponding to each first target object; and assigning each first target object to the second target object in the second target object set based on the score, wherein the second target object and the first target object have a preset association relationship, thereby achieving the purpose of jointly learning and understanding users and customer service personnel based on the deep learning model, and finally classifying users more scientifically, thereby achieving the technical effect of greatly improving the recommendation success rate, and thus solving the technical problem of low recommendation success rate caused by the inability of historical usage records and business rules to pay attention to the real demands of users in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a flowchart of a method for matching a target object according to an embodiment of the present application;

[0020] Figure 2 This is a flowchart of multi-customer service matching recommendation in an optional embodiment of the present application;

[0021] Figure 3 is a schematic structural diagram of a target object matching device according to an embodiment of the present application;

[0022] Figure 4 is a schematic block diagram of an example electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present application, an embodiment of a method for matching a target object is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 A target object matching method according to an embodiment of the present application is applied in a multi-customer service scenario, such as Figure 1 As shown, the method comprises the following steps:

[0027] Step S102, obtaining first information of each first object in the first set under multiple different first dimensions;

[0028] Step S104, obtaining second messages of each second object in the second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object;

[0029] Step S106, constructing a multi-task deep learning model according to the first information and the second information, and obtaining first target information of each first target object in the first target object set under multiple different first dimensions;

[0030] Step S108, inputting the first target information into the multi-task deep learning model to obtain scores corresponding to each first target object;

[0031] Step S110: allocating each first target object to a second target object in a second target object set based on the score, wherein the second target object has a preset association relationship with the first target object.

[0032] It should be noted that the first set may be a user group, and the first object may be a user. It is easy to notice that the second set may be a group corresponding to customer service personnel, and the second object may be a customer service personnel (referred to as customer service). It should be noted that the preset association relationship is a service relationship between customer service personnel and users.

[0033] In the target object matching method, first information of each first object in the first set under multiple different first dimensions is obtained; second information of each second object in the second set under multiple different second dimensions is obtained, wherein a preset association relationship exists between the first object and the second object; a multi-task deep learning model is constructed according to the first information and the second information, and the first target information of each first target object in the first target object set under multiple different first dimensions is obtained; the first target information is input into the multi-task deep learning model to obtain a score corresponding to each first target object; and each first target object is assigned to a second target object in the second target object set based on the score, wherein a preset association relationship exists between the second target object and the first target object, thereby achieving the purpose of jointly learning and understanding users and customer service personnel based on the deep learning model, and finally classifying users more scientifically, thereby achieving the technical effect of greatly improving the recommendation success rate, and further solving the technical problem of low recommendation success rate caused by the inability of historical usage records and business rules to pay attention to the real demands of users in related technologies.

[0034] In some embodiments of the present application, assigning each first target object to a second target object in a set of second target objects based on a score can be achieved in the following manner: determining the priority of the first target object according to the score corresponding to each first target object, wherein the higher the priority, the greater the success rate of the second target object and the first target object to reach a transaction; obtaining the business indicator corresponding to each second target object in the set of second target objects, wherein the larger the business indicator, the stronger the business capability of the second target object; assigning each first target object to the second target object in the set of second target objects according to the business indicator and priority.

[0035] Specifically, the priority of the first target object is determined according to the score corresponding to each first target object, including: sorting the score corresponding to each first target object based on a predetermined size order to obtain a first sorting result; dividing the first target object into multiple groups of first subsets based on a preset interval and the first sorting result, wherein the priority of each subset in the multiple groups of first subsets is different; and determining the priority of the first subset to which each first target object belongs as the priority corresponding to the first target object.

[0036] Optionally, each first target object is assigned to a second target object in a second target object set according to business indicators and priorities, including: determining a first group number corresponding to multiple groups of subsets; and assigning each first target object to a second target object in a second target object set according to the first group number and business indicators.

[0037] As an optional implementation, each first target object is assigned to a second target object in a second target object set according to a first group number and a business indicator, and the business indicator can be sorted based on a predetermined size order to obtain a second sorting result; each second target object in the second target object set is grouped into multiple second subsets based on the first group number; the first subset is assigned to the second subset, wherein the greater the business indicator to which the subset belongs, the higher the priority of the first subset assigned to the second subset.

[0038] In some other optional embodiments of the present application, each first target object is assigned to a second target object in a second target object set based on a score, including: dividing each first target object in the first target object set according to the size of the score corresponding to each first target object to obtain a division result, wherein the division result at least includes: low-scoring objects and high-scoring objects, wherein the recommendation success rate of the low-scoring objects is lower than the recommendation success rate of the high-scoring objects; combining the high-scoring objects with the low-scoring objects in a predetermined ratio to obtain a combined set to be assigned; and matching the set to be assigned to any second target object in the second target object set.

[0039] In an exemplary embodiment of the present application, constructing a multi-task deep learning model based on the first information and the second information can be achieved in the following manner. Specifically, the first information and the second information are respectively encoded to obtain first encoded data and second encoded data; receiving an input annotation result, and constructing a multi-task learning model based on the first encoded data, the second encoded data and the annotation result.

[0040] In some instances of the present application, obtaining first information of each first object in a first set under multiple different first dimensions may include: determining a first identifier corresponding to each first object; calling a language processing algorithm to standardize data information corresponding to the first identifier to obtain data information with a table structure, and determining that the data information with the table structure is the first information; obtaining second information of each second object in a second set under multiple different second dimensions includes: determining a second identifier corresponding to each second object; calling a language processing algorithm to standardize data information corresponding to the second identifier to obtain data information with a table structure, and determining that the data information with the table structure is the second information.

[0041] Figure 2 : is a flowchart of multiple customer service recommendation matching in an optional embodiment of the present application, such as Figure 2 As shown in the figure, the implementation of this method mainly includes five steps: user attribute and consumption record analysis, customer service staff attribute and performance record analysis, customer service staff and user communication record analysis, user customer service staff deep learning recommendation model, and multi-customer service recommendation post-processing model. The specific execution actions after decomposition of each step are as follows:

[0042] Step 1: Analysis of user attributes and consumption records:

[0043] Based on system data, a corresponding relationship is established between the user's basic information and consumption records, and each element involved is extended; through natural language processing, semantic understanding, and keyword capture, data without table structure is standardized and corrected, and through different primary key information, as much user-related data information with table structure as possible is extracted from each system.

[0044] Extract four types of key information:

[0045]

[0046]

[0047] Step 2: Analysis of customer service staff attributes and performance records:

[0048] Based on system data, a correspondence is established between the basic information of customer service personnel, historical order information, and corresponding performance and incentive information, and key information is extracted for each factor involved. Through natural language processing, semantic understanding, and keyword capture, data that does not have a table structure is standardized and corrected, and through a hierarchical analysis of service capabilities, the service level of customer service personnel is personalized.

[0049] Extract four types of key information:

[0050]

[0051]

[0052] Step 3: Analysis of communication records between customer service staff and users: Extract and organize the data related to the recordings based on the recording data in the system; collect information from the recordings through deep learning, emotion recognition and other means, and associate it with the user analysis results or customer service staff analysis results.

[0053] Extract four types of key information:

[0054]

[0055]

[0056] Step 4: User customer service staff deep learning recommendation model:

[0057] Encode the key information extracted by the user and the key information extracted by the customer service staff and convert them into floating point numbers; build a deep learning model according to the recommended goals and use the model for multi-task learning. Deep learning model construction:

[0058]

[0059]

[0060] Step 5: Build a post-processing model for multi-customer service recommendation: Consider the relevant restrictions of actual operational production requirements, deepen user understanding, and tune the model results through post-processing of the results; calculate the final score for the user, prioritize the users according to the final user score and the allocation capacity of the existing customer service personnel, and segment the users according to the priority classification results.

[0061] Post-processing model construction:

[0062]

[0063] It is easy to notice that by accurately understanding users, accurately grouping users, and matching users and service personnel, customer service personnel can recommend more suitable products to users, thereby improving user understanding, and then improving user satisfaction and the degree of fit between needs; secondly, the above methods can be more in line with the mission and goals of manual services, using the right people to serve the right users, and improving the service efficiency of customer service personnel; finally, with a limited number of customer service personnel, telephone communication with user groups with high success rates and high returns can be carried out with the greatest efficiency, thereby maximizing the effectiveness of business recommendations.

[0064] Figure 3 A target object matching device according to an embodiment of the present application can be applied to multiple customer service scenarios, such as Figure 3 As shown, the device comprises:

[0065] A first acquisition module 30, configured to acquire first information of each first object in the first set under a plurality of different first dimensions;

[0066] A second acquisition module 32 is used to acquire second messages of each second object in the second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object;

[0067] A construction module 34 is used to construct a multi-task deep learning model according to the first information and the second information, and obtain first target information of each first target object in the first target object set under multiple different first dimensions;

[0068] An input module 36, used to input the first target information into the multi-task deep learning model to obtain scores corresponding to each first target object;

[0069] The allocation module 38 is configured to allocate each first target object to a second target object in the second target object set based on the score, wherein the second target object has a preset association relationship with the first target object.

[0070] In the device, a first acquisition module 30 is used to obtain first information of each first object in the first set under multiple different first dimensions; a second acquisition module 32 is used to obtain second information of each second object in the second set under multiple different second dimensions, wherein the first object and the second object have a preset association relationship; a construction module 34 is used to construct a multi-task deep learning model based on the first information and the second information, and obtain the first target information of each first target object in the first target object set under multiple different first dimensions; an input module 36 is used to input the first target information into the multi-task deep learning model to obtain the score corresponding to each first target object; an allocation module 48 is used to allocate each first target object to a second target object in the second target object set based on the score, wherein the second target object and the first target object have a preset association relationship, thereby achieving the purpose of jointly learning and understanding users and customer service personnel based on the deep learning model, and finally classifying users more scientifically, thereby achieving the technical effect of greatly improving the recommendation success rate, and thus solving the technical problem of low recommendation success rate caused by the inability of historical usage records and business rules to pay attention to the real demands of users in related technologies.

[0071] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any target object matching method.

[0072] Specifically, the above storage medium is used to store program instructions for the following functions to implement the following functions:

[0073] Obtain first information of each first object in the first set under multiple different first dimensions; obtain second information of each second object in the second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object; construct a multi-task deep learning model based on the first information and the second information, and obtain first target information of each first target object in the first target object set under multiple different first dimensions; input the first target information into the multi-task deep learning model to obtain a score corresponding to each first target object; assign each first target object to a second target object in the second target object set based on the score, wherein a preset association relationship exists between the second target object and the first target object.

[0074] Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above-mentioned contents. More specific examples of the above-mentioned storage medium may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above-mentioned contents.

[0075] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any target object matching method.

[0076] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0077] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0078] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0079] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0080] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the matching method of the target object. For example, in some embodiments, the matching method of the target object may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the matching method of the target object described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the matching method of the target object by any other appropriate means (e.g., by means of firmware).

[0081] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0082] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0083] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 foregoing.

[0084] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0085] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0086] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0087] In the relevant embodiments of the present application, effective key information extraction is adopted for user data and multi-customer service personnel data to effectively expand the data scope understood by users, by obtaining the first information of each first object in the first set under multiple different first dimensions; obtaining the second message of each second object in the second set under multiple different second dimensions, wherein the first object and the second object have a preset association relationship; constructing a multi-task deep learning model based on the first information and the second information, and obtaining the first target information of each first target object in the first target object set under multiple different first dimensions; inputting the first target information into the multi-task deep learning model to obtain the score corresponding to each first target object; and assigning each first target object to the second target object in the second target object set based on the score, wherein the second target object and the first target object have a preset association relationship, thereby achieving the purpose of joint learning and understanding of users and customer service personnel based on the deep learning model, and finally classifying users more scientifically, thereby achieving the technical effect of greatly improving the recommendation success rate, and thus solving the technical problem of low recommendation success rate caused by the inability of historical usage records and business rules to pay attention to the real demands of users in the related technologies.

[0088] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0089] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0092] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0094] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for matching a target object, characterized in that: The method is applied in a multi-customer service scenario, including: Acquire first information of each first object in the first set under a plurality of different first dimensions, wherein the first object is a user; Acquire second information of each second object in the second set under multiple different second dimensions, wherein a preset association relationship exists between the first object and the second object, and the second object is a customer service staff; Building a multi-task deep learning model according to the first information and the second information, and obtaining first target information of each first target object in the first target object set under the multiple different first dimensions; Inputting the first target information into the multi-task deep learning model to obtain scores corresponding to each of the first target objects; Allocating each of the first target objects to a second target object in a second target object set based on the score, wherein the second target object has the preset association relationship with the first target object, and the preset association relationship is a service relationship between the customer service staff and the user; The step of allocating each of the first target objects to a second target object in the set of second target objects based on the score comprises: Sorting the scores corresponding to the first target objects based on a predetermined order of magnitude to obtain a first sorting result; dividing the first target objects into a plurality of first subsets based on a preset interval and the first sorting result, wherein the priorities of the subsets in the plurality of first subsets are different; determining the priority of the first subset to which the first target objects belong as the priority corresponding to the first target object, wherein the higher the priority, the greater the success rate of the second target object to reach a transaction with the first target object; Acquire a business indicator corresponding to each second target object in the second target object set, wherein the larger the business indicator, the stronger the business capability of the second target object; Determine a first group number corresponding to the multiple groups of first subsets; sort the business indicators based on a predetermined size order to obtain a second sorting result; divide each second target object in the second target object set into multiple groups of second subsets based on the first group number; assign the first subset to the second subset, wherein the larger the business indicator to which the subset belongs, the higher the priority of the first subset assigned to the second subset.

2. The method according to claim 1, characterized in that: Allocating each of the first target objects to a second target object in a set of second target objects based on the score comprises: According to the scores corresponding to the first target objects, each of the first target objects in the first target object set is divided to obtain a division result, wherein the division result at least includes: low-score objects and high-score objects, wherein the recommendation success rate of the low-score objects is lower than the recommendation success rate of the high-score objects; Combining the high-scoring objects with the low-scoring objects according to a predetermined ratio to obtain a combined set to be allocated; The to-be-allocated set is matched to any second target object in the second target object set.

3. The method according to claim 1, characterized in that Constructing a multi-task deep learning model according to the first information and the second information, including: Encoding the first information and the second information respectively to obtain first encoded data and second encoded data; Receive input annotation results, and build the multi-task deep learning model according to the first encoded data, the second encoded data, and the annotation results.

4. The method according to claim 1, characterized in that: Acquiring first information of each first object in the first set under a plurality of different first dimensions includes: Determine a first identifier corresponding to each first object; call a language processing algorithm to perform standardization processing on the data information corresponding to the first identifier to obtain data information with a table structure, and determine that the data information with the table structure is the first information; Obtaining second information of each second object in the second set under multiple different second dimensions includes: Determine a second identifier corresponding to each second object; call a language processing algorithm to standardize the data information corresponding to the second identifier to obtain data information with a table structure, and determine that the data information with the table structure is the second information.

5. A target object matching device, characterized in that: The device is applied in a multi-customer service scenario, including: A first acquisition module, configured to acquire first information of each first object in the first set under a plurality of different first dimensions, wherein the first object is a user; A second acquisition module is used to acquire second information of each second object in the second set under multiple different second dimensions, wherein the first object has a preset association relationship with the second object, and the second object is a customer service staff; A construction module, configured to construct a multi-task deep learning model according to the first information and the second information, and obtain first target information of each first target object in the first target object set under the multiple different first dimensions; An input module, used to input the first target information into the multi-task deep learning model to obtain scores corresponding to each of the first target objects; an allocation module, configured to allocate each of the first target objects to a second target object in a set of second target objects based on the score, wherein the second target object has the preset association relationship with the first target object, and the preset association relationship is a service relationship between the customer service staff and the user; The step of allocating each of the first target objects to a second target object in the set of second target objects based on the score comprises: Sorting the scores corresponding to the first target objects based on a predetermined order of magnitude to obtain a first sorting result; dividing the first target objects into a plurality of first subsets based on a preset interval and the first sorting result, wherein the priorities of the subsets in the plurality of first subsets are different; determining the priority of the first subset to which the first target objects belong as the priority corresponding to the first target object, wherein the higher the priority, the greater the success rate of the second target object to reach a transaction with the first target object; Acquire a business indicator corresponding to each second target object in the second target object set, wherein the larger the business indicator, the stronger the business capability of the second target object; Determine a first group number corresponding to the multiple groups of first subsets; sort the business indicators based on a predetermined size order to obtain a second sorting result; divide each second target object in the second target object set into multiple groups of second subsets based on the first group number; assign the first subset to the second subset, wherein the larger the business indicator to which the subset belongs, the higher the priority of the first subset assigned to the second subset.

6. A non-volatile storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the target object matching method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the target object matching method as described in any one of claims 1 to 4.

Images