Product recommendation method and device, computer equipment and storage medium

Abstract

The invention provides a product recommendation method and apparatus, a computer device and a storage medium. The method comprises the steps of obtaining text data for performing a session with a target user; performing natural language processing on the text data to obtain N feature fields; the feature field is used for representing the product intention of the target user, and N is a positive integer; determining N product sets in one-to-one correspondence with the N feature fields, wherein each product set comprises at least one product; determining a target product based on the N product sets; and pushing the target product to the target user. According to the method and the device, natural language processing is performed on the text data of the conversation with the target user, so that the product intention of the target user is determined, and the target product meeting the product intention of the target user is pushed to the target user based on the product intention of the target user, so that personalized product recommendation is performed based on the user conversation, and the user experience is improved. The purchase desire of the user is improved, and the user conversion rate is improved.

Description

Technical Field

[0001] The present invention relates to the fields of natural language processing technology and financial insurance, and in particular to a product recommendation method, device, computer equipment and storage medium. Background Art

[0002] In the field of finance and insurance, intelligent customer service for answering user inquiries is an effective way to reach user needs. By establishing dialogues with users and recommending relevant insurance products to users, intelligent customer service can expand insurance marketing channels.

[0003] However, existing intelligent customer service only pushes fixed insurance products to all users and is unable to recommend insurance products in a personalized manner based on user conversations, resulting in poor product recommendation results and low user conversion rates. Summary of the invention

[0004] The main purpose of the present invention is to provide a product recommendation method, device, computer equipment and storage medium, aiming to solve the technical problems of poor product recommendation effect and low user conversion rate.

[0005] To achieve the above object, the present invention provides a product recommendation method, which comprises:

[0006] Obtain text data of conversations with target users;

[0007] Performing natural language processing on the text data to obtain N feature fields; the feature fields are used to characterize the product intention of the target user, and N is a positive integer;

[0008] Determine N product sets corresponding one-to-one to the N characteristic fields, each of the product sets including at least one product;

[0009] Determine a target product based on the N product sets;

[0010] The target product is pushed to the target user.

[0011] Optionally, the natural language processing is performed on the text data to obtain N feature fields, including:

[0012] Performing word segmentation processing on the text data to obtain M fields included in the text data, where M is a positive integer greater than N;

[0013] Inputting the M fields into a preset natural language processing model;

[0014] Through the natural language processing model, the field representing the product intention of the target user in the M fields is determined as a feature field, so as to obtain N feature fields.

[0015] Optionally, the N characteristic fields include a first field characterizing product requirements, and the determining of N product sets corresponding one-to-one to the N characteristic fields includes:

[0016] For a first field among the N feature fields, a product attribute field associated with the first field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of product attribute fields, and the product demand represented by the first field is the same as the product attribute represented by the product attribute field associated with the first field;

[0017] querying the product attribute field associated with the first field in the product attribute library to determine at least one product corresponding to the first field; the product attribute library stores a mapping relationship between product attribute fields and products;

[0018] Based on at least one product corresponding to the first field, a product set corresponding to the first field is generated.

[0019] Optionally, the N characteristic fields include a second field representing risk preference, and the determining of N product sets corresponding one-to-one to the N characteristic fields includes:

[0020] For a second field in the N characteristic fields, determining a risk attribute field associated with the second field in a preset product attribute library through a preset natural language processing model; the product attribute library includes a plurality of risk attribute fields, and the risk preference represented by the second field is the same as the risk attribute represented by the risk attribute field associated with the second field;

[0021] querying the risk attribute field associated with the second field in the product attribute library to determine at least one product corresponding to the second field; the product attribute library stores a mapping relationship between the risk attribute field and the product;

[0022] Based on the at least one product corresponding to the second field, a product set corresponding to the second field is generated.

[0023] Optionally, the N characteristic fields include a third field representing a product budget, and determining N product sets corresponding one-to-one to the N characteristic fields includes:

[0024] For a third field in the N characteristic fields, a budget attribute field associated with the third field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of budget attribute fields, and the product budget represented by the third field is the same as the budget attribute represented by the budget attribute field associated with the third field;

[0025] Querying the budget attribute field associated with the third field in the product attribute library to determine at least one product corresponding to the third field; the product attribute library stores a mapping relationship between the budget attribute field and the product;

[0026] Based on the at least one product corresponding to the third field, a product set corresponding to the third field is generated.

[0027] Optionally, determining the target product based on the N product sets includes:

[0028] Determine the products included in each of the N product sets;

[0029] The products included in each of the product sets are determined as target products.

[0030] Optionally, the pushing the target product to the target user includes:

[0031] Searching for the target product in a preset product knowledge base; the product knowledge base stores a mapping relationship between products and product information;

[0032] Determine the product information that has a mapping relationship with the target product as the target product information;

[0033] Converting the target product information into natural language text through a preset natural language processing model;

[0034] The natural language text is pushed to the target user.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a product recommendation device, the product recommendation device comprising:

[0036] An acquisition module, used to acquire text data of a conversation with a target user;

[0037] A processing module, used for performing natural language processing on the text data to obtain N feature fields; the feature fields are used to represent the product intention of the target user, and N is a positive integer;

[0038] A first determining module is used to determine N product sets corresponding to the N characteristic fields one by one, each of the product sets including at least one product;

[0039] A second determination module, configured to determine a target product based on the N product sets;

[0040] A push module is used to push the target product to the target user.

[0041] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0042] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the product recommendation methods proposed in the embodiments of the present application are implemented.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0044] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the product recommendation methods proposed in the embodiments of the present application are implemented.

[0045] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0046] The present invention provides a product recommendation method, device, computer equipment and storage medium, the method comprising: obtaining text data of a conversation with a target user; performing natural language processing on the text data to obtain N feature fields; the feature fields are used to characterize the product intention of the target user, N being a positive integer; determining N product sets corresponding to the N feature fields, each product set including at least one product; determining the target product based on the N product sets; and pushing the target product to the target user. In the present invention, natural language processing is performed on the text data of a conversation with the target user to determine the product intention of the target user, and based on the product intention of the target user, a target product that meets the product intention of the target user is pushed to the target user, thereby recommending products in a personalized manner based on user conversations, thereby increasing the user's desire to buy and improving the user conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0049] Figure 2 is a flow chart of a product recommendation method provided by an embodiment of the present invention;

[0050] Figure 3 is a structural schematic diagram of an embodiment of a product recommendation device according to the present application;

[0051] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0052] The product recommendation method provided by the embodiment of the present invention is applied to the product recommendation device. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0053] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] 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 accompanying drawings.

[0055] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0056] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0057] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0058] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0059] It should be noted that the product recommendation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the product recommendation device is generally set in the server / terminal device.

[0060] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0061] Continue to refer Figure 2 , showing a flow chart of an embodiment of the product recommendation method proposed in the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology. In order to clearly explain the need for the technical solution, the subsequent embodiments use the recommendation of insurance products as an example to illustrate the technical solution. It should be understood that the product recommendation method provided in the embodiment of the present invention can recommend financial products, loan products and other products in addition to insurance products.

[0062] The product recommendation method provided by the embodiment of the present invention comprises the following steps:

[0063] S210, obtaining text data of a conversation with a target user.

[0064] As described above, the product recommendation method provided by the embodiment of the present invention can be applied to a product recommendation device. In an optional application scenario, the product recommendation device runs an intelligent customer service robot. In the above application scenario, after the intelligent user robot establishes a conversation with the user, the text data of the conversation with the target user is obtained. The above text data includes the conversation text of the intelligent customer service robot and the target user.

[0065] S220, performing natural language processing on the text data to obtain N feature fields.

[0066] As mentioned above, the text data includes dialogue text. In this step, after acquiring the text data, natural language processing is performed on the text data to obtain N feature fields.

[0067] The above-mentioned characteristic field is used to characterize the product intention of the target user, and N is a positive integer.

[0068] Optionally, the above-mentioned characteristic field is composed of words. For example, the product recommended by the embodiment of the present invention is an insurance product. If the characteristic field is "car insurance", the product intention represented by the characteristic field is "car insurance".

[0069] S230, determining N product sets corresponding one-to-one to the N characteristic fields.

[0070] In this step, the product set corresponding to each characteristic field can be determined according to the N characteristic fields, that is, N product sets corresponding to the N characteristic fields can be determined one by one, wherein each product set includes at least one product.

[0071] For specific implementation methods of how to determine the product set corresponding to the feature field, please refer to the subsequent embodiments.

[0072] S240: Determine a target product based on the N product sets.

[0073] After N product sets are determined, a target product may be determined based on at least one product included in each product set.

[0074] S250: Push the target product to the target user.

[0075] Optionally, after the target product is determined, product information is sent to the user via an intelligent customer service robot to recommend the target product to the user.

[0076] It should be understood that after pushing the target product to the target user, if feedback information from the target user on the target product is received, the feedback information can be processed by the natural language processing model to obtain the product intention of the user feedback, and the product can be pushed to the target user again based on the product intention to optimize the push results.

[0077] In this embodiment, the text data of the conversation with the target user is obtained; the text data is subjected to natural language processing to obtain N feature fields; N product sets corresponding to the N feature fields are determined; based on the N product sets, the target product is determined; and the target product is pushed to the target user. In this embodiment, the text data of the conversation with the target user is subjected to natural language processing to determine the product intention of the target user, and the target product that meets the product intention of the target user is pushed to the target user based on the product intention of the target user, thereby recommending personalized products based on user conversations, thereby increasing the user's desire to buy and improving the user conversion rate.

[0078] Optionally, the natural language processing is performed on the text data to obtain N feature fields, including:

[0079] Performing word segmentation processing on the text data to obtain M fields included in the text data, where M is a positive integer greater than N;

[0080] Inputting the M fields into a preset natural language processing model;

[0081] Through the natural language processing model, the field representing the product intention of the target user in the M fields is determined as a feature field, so as to obtain N feature fields.

[0082] In this embodiment, a natural language processing model is pre-set. Optionally, the natural language processing model is an NLP model with large-scale data processing capabilities.

[0083] In this embodiment, after obtaining the text data of the conversation between the intelligent customer service robot and the user, the text data is segmented and divided into M fields, where M is a positive integer greater than N.

[0084] Furthermore, the above M fields are input into a preset natural language processing model, the field meaning represented by each field is analyzed by the natural language processing model, and the field representing the product intention of the target user among the M fields is determined as a feature field, thereby obtaining N feature fields.

[0085] Exemplarily, the above-mentioned characteristic field may be a field characterizing product demand, such as "life insurance"; the above-mentioned characteristic field may be a characteristic field characterizing risk preference, such as "low risk"; the above-mentioned characteristic field may be a field characterizing product budget, such as "budget is 20,000".

[0086] In this embodiment, by utilizing the natural language understanding, generation, and reasoning capabilities of the large model, it is possible to more accurately understand the insurance needs, risk preferences, and product budgets expressed or implied by the user in the conversation. Thus, the feature fields determined by the natural language processing model can accurately characterize the user's product intentions.

[0087] Optionally, the N characteristic fields include a first field characterizing product requirements, and the determining of N product sets corresponding one-to-one to the N characteristic fields includes:

[0088] For a first field among the N feature fields, a product attribute field associated with the first field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of product attribute fields, and the product demand represented by the first field is the same as the product attribute represented by the product attribute field associated with the first field;

[0089] querying the product attribute field associated with the first field in the product attribute library to determine at least one product corresponding to the first field; the product attribute library stores a mapping relationship between product attribute fields and products;

[0090] Based on at least one product corresponding to the first field, a product set corresponding to the first field is generated.

[0091] As described above, the characteristic field includes a field that characterizes product requirements, such as "personal insurance", and the field that characterizes product requirements can be referred to as the first field. A natural language processing model and a product attribute library are pre-set, and the product attribute library contains products of various types and ranges, and each product has corresponding attributes, conditions, fees, compensation and other information. In addition, the product attribute library stores the mapping relationship between product attribute fields and products, wherein the above-mentioned product attribute fields are used to characterize product attributes, for example, a certain product attribute field represents "personal insurance coverage".

[0092] In this embodiment, a product attribute field associated with the first field in a preset product attribute library is determined through a natural language processing model. Specifically, a semantic analysis is performed on each product attribute field in the product attribute library through a natural language processing model to determine a product attribute field representing a product attribute that is the same as the product requirement represented by the first field.

[0093] The product attribute field associated with the first field is queried in the product attribute library to determine at least one product that has a mapping relationship with the first field, and the at least one product is divided into the same set to obtain a product set corresponding to the first field.

[0094] In this embodiment, the product needs of the target user are determined through a natural language processing model, and then the products that meet the product needs are determined through a preset product attribute library, thereby determining the products that meet the user's intentions.

[0095] Optionally, the N characteristic fields include a second field representing risk preference, and the determining of N product sets corresponding one-to-one to the N characteristic fields includes:

[0096] For a second field in the N characteristic fields, determining a risk attribute field associated with the second field in a preset product attribute library through a preset natural language processing model; the product attribute library includes a plurality of risk attribute fields, and the risk preference represented by the second field is the same as the risk attribute represented by the risk attribute field associated with the second field;

[0097] querying the risk attribute field associated with the second field in the product attribute library to determine at least one product corresponding to the second field; the product attribute library stores a mapping relationship between the risk attribute field and the product;

[0098] Based on the at least one product corresponding to the second field, a product set corresponding to the second field is generated.

[0099] As described above, the characteristic field includes a field representing risk preference, such as "low risk", and the field representing risk preference may be referred to as the second field. A natural language processing model and a product attribute library are pre-set, and the product attribute library stores a mapping relationship between risk attribute fields and products, wherein the risk attribute fields are used to represent risk attributes, for example, a certain risk attribute field represents "the product is high risk".

[0100] In this embodiment, a risk attribute field associated with the second field in a preset product attribute library is determined through a natural language processing model. Specifically, a semantic analysis is performed on each risk attribute field in the product attribute library through the natural language processing model to determine a risk attribute field that represents the same risk attribute as the risk preference represented by the second field.

[0101] The risk attribute field associated with the second field is queried in the product attribute library to determine at least one product that has a mapping relationship with the second field, and the at least one product is divided into the same set to obtain a product set corresponding to the second field.

[0102] In this embodiment, the risk preference of the target user is determined through a natural language processing model, and then the products that meet the risk preference of the target user are determined through a preset product attribute library, so as to determine the products that meet the user's intentions, and then in subsequent steps, the products of the user's intentions are pushed to the user to increase the user's desire to buy.

[0103] Optionally, the N characteristic fields include a third field representing a product budget, and determining N product sets corresponding one-to-one to the N characteristic fields includes:

[0104] For a third field in the N characteristic fields, a budget attribute field associated with the third field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of budget attribute fields, and the product budget represented by the third field is the same as the budget attribute represented by the budget attribute field associated with the third field;

[0105] Querying the budget attribute field associated with the third field in the product attribute library to determine at least one product corresponding to the third field; the product attribute library stores a mapping relationship between the budget attribute field and the product;

[0106] Based on the at least one product corresponding to the third field, a product set corresponding to the third field is generated.

[0107] As described above, the characteristic field includes a field representing the product budget, such as "the budget is 20,000", and the field representing the product budget can be called the third field. A natural language processing model and a product attribute library are pre-set, and the product attribute library stores the mapping relationship between the budget attribute field and the product, wherein the budget attribute field is used to represent the budget attribute, for example, a budget attribute field represents "the cost of the product is 30,000".

[0108] In this embodiment, a budget attribute field associated with the third field in a preset product attribute library is determined through a natural language processing model. Specifically, a semantic analysis is performed on each budget attribute field in the product attribute library through a natural language processing model to determine a budget attribute field representing a budget attribute that is the same as the product budget represented by the third field.

[0109] The budget attribute field associated with the third field is queried in the product attribute library to determine at least one product having a mapping relationship with the third field, and the at least one product is divided into the same set to obtain a product set corresponding to the third field.

[0110] In this embodiment, the product budget of the target user is determined through a natural language processing model, and then the products that meet the target user's budget are determined through a preset product attribute library, so as to determine the products that meet the user's intentions, and then in subsequent steps, the products of the user's intentions are pushed to the user to increase the user's desire to buy.

[0111] Optionally, determining the target product based on the N product sets includes:

[0112] Determine the products included in each of the N product sets;

[0113] The products included in each of the product sets are determined as target products.

[0114] As mentioned above, a product set includes at least one product.

[0115] In this embodiment, the products included in each of the N product sets are determined, and then the products included in each product set are determined as target products.

[0116] For example, product set 1 includes "auto insurance product 1" and "auto insurance product 2", product set 2 includes "auto insurance product 1", "life insurance product 1" and "life insurance product 2", and product set 3 includes "auto insurance product 1", "auto insurance product 2" and "life insurance product 2", then "auto insurance product 1" included in product set 1, product set 2 and product set 3 is determined as the target product.

[0117] In other implementations, after N product sets are determined, if each product set includes multiple products, any one of the multiple products is determined as a target product.

[0118] It should be noted that the products included in each product set are all products that meet the product intentions of the target user. In this embodiment, the products included in each product set are determined as target products, so as to determine the target product that best meets the product intentions of the target user from the multiple products included in the product set.

[0119] Optionally, the pushing the target product to the target user includes:

[0120] Querying the target product in a preset product knowledge base; the product knowledge base stores a mapping relationship between products and product information;

[0121] Determine the product information that has a mapping relationship with the target product as the target product information;

[0122] Converting the target product information into natural language text through a preset natural language processing model;

[0123] The natural language text is pushed to the target user.

[0124] In this embodiment, a product knowledge base is pre-set, which stores the mapping relationship between products and product information, wherein the above-mentioned product information includes various types and ranges of insurance-related knowledge, and each insurance-related knowledge has corresponding definitions, classifications, rules, cases and other information.

[0125] In this embodiment, the target product is input into the product knowledge base for query to obtain the target product information that has a mapping relationship with the target product. The target product information is converted into natural language text through the natural language processing model, and then the natural language text is pushed to the target user to introduce and recommend the selected products to the user in the form of natural language.

[0126] Optionally, in other implementations, while pushing the natural language text to the target user, a purchase link of the target product is also pushed to the target user, so that the target user can purchase the target product.

[0127] In this embodiment, after determining the target product, the target product information of the target product is determined based on a preset product knowledge base, and then the target product information is converted into natural language text based on a natural language processing model, so as to introduce and recommend the selected products to users in the form of natural language, thereby increasing the user's interest in the product and improving the user's conversion rate.

[0128] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a product recommendation device 300. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0129] An embodiment of the present invention provides a product recommendation device 300, which includes:

[0130] An acquisition module 310 is used to acquire text data of a conversation with a target user;

[0131] The processing module 320 is used to perform natural language processing on the text data to obtain N feature fields; the feature fields are used to represent the product intention of the target user, and N is a positive integer;

[0132] A first determining module 330 is used to determine N product sets corresponding to the N characteristic fields one by one, each of the product sets including at least one product;

[0133] A second determination module 340 is used to determine a target product based on the N product sets;

[0134] The push module 350 is used to push the target product to the target user.

[0135] Optionally, the processing module 320 is specifically configured to:

[0136] Performing word segmentation processing on the text data to obtain M fields included in the text data, where M is a positive integer greater than N;

[0137] Inputting the M fields into a preset natural language processing model;

[0138] Through the natural language processing model, the field representing the product intention of the target user in the M fields is determined as a feature field, so as to obtain N feature fields.

[0139] Optionally, the N characteristic fields include a first field representing product requirements, and the first determining module 330 is specifically configured to:

[0140] For a first field among the N feature fields, a product attribute field associated with the first field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of product attribute fields, and the product demand represented by the first field is the same as the product attribute represented by the product attribute field associated with the first field;

[0141] querying the product attribute field associated with the first field in the product attribute library to determine at least one product corresponding to the first field; the product attribute library stores a mapping relationship between product attribute fields and products;

[0142] Based on at least one product corresponding to the first field, a product set corresponding to the first field is generated.

[0143] Optionally, the N characteristic fields include a second field representing risk preference, and the first determination module 330 is further specifically configured to:

[0144] For a second field in the N characteristic fields, determining a risk attribute field associated with the second field in a preset product attribute library through a preset natural language processing model; the product attribute library includes a plurality of risk attribute fields, and the risk preference represented by the second field is the same as the risk attribute represented by the risk attribute field associated with the second field;

[0145] querying the risk attribute field associated with the second field in the product attribute library to determine at least one product corresponding to the second field; the product attribute library stores a mapping relationship between the risk attribute field and the product;

[0146] Based on the at least one product corresponding to the second field, a product set corresponding to the second field is generated.

[0147] Optionally, the N characteristic fields include a third field representing a product budget, and the first determining module 330 is further specifically configured to:

[0148] For a third field in the N characteristic fields, a budget attribute field associated with the third field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of budget attribute fields, and the product budget represented by the third field is the same as the budget attribute represented by the budget attribute field associated with the third field;

[0149] Querying the budget attribute field associated with the third field in the product attribute library to determine at least one product corresponding to the third field; the product attribute library stores a mapping relationship between the budget attribute field and the product;

[0150] Based on the at least one product corresponding to the third field, a product set corresponding to the third field is generated.

[0151] Optionally, the second determining module 340 is specifically configured to:

[0152] Determine the products included in each of the N product sets;

[0153] The products included in each of the product sets are determined as target products.

[0154] Optionally, the push module 350 is specifically used to:

[0155] Querying the target product in a preset product knowledge base; the product knowledge base stores a mapping relationship between products and product information;

[0156] Determine the product information that has a mapping relationship with the target product as the target product information;

[0157] Converting the target product information into natural language text through a preset natural language processing model;

[0158] The natural language text is pushed to the target user.

[0159] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0160] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0161] The computer device may be a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with the user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0162] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the product recommendation method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0163] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the product recommendation method.

[0164] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0165] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the product recommendation program, and the product recommendation program can be executed by at least one processor so that the at least one processor performs the steps of the product recommendation method as described above.

[0166] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0167] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0168] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A product recommendation method, It is characterized in that include: Obtain text data of conversations with target users; Performing natural language processing on the text data to obtain N feature fields; The feature field is used to represent the product intention of the target user, and N is a positive integer; Determine N product sets corresponding one-to-one to the N characteristic fields, each of the product sets including at least one product; Determine a target product based on the N product sets; The target product is pushed to the target user.

2. The method according to claim 1, It is characterized in that The natural language processing is performed on the text data to obtain N feature fields, including: Performing word segmentation processing on the text data to obtain M fields included in the text data, where M is a positive integer greater than N; Inputting the M fields into a preset natural language processing model; Through the natural language processing model, the field representing the product intention of the target user in the M fields is determined as a feature field, so as to obtain N feature fields.

3. The method according to claim 1, It is characterized in that The N characteristic fields include a first field representing product requirements, and the determining of N product sets corresponding to the N characteristic fields one-to-one includes: For a first field among the N feature fields, a product attribute field associated with the first field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of product attribute fields, and the product demand represented by the first field is the same as the product attribute represented by the product attribute field associated with the first field; querying the product attribute field associated with the first field in the product attribute library to determine at least one product corresponding to the first field; the product attribute library stores a mapping relationship between product attribute fields and products; Based on at least one product corresponding to the first field, a product set corresponding to the first field is generated.

4. The method according to claim 1, It is characterized in that The N characteristic fields include a second field representing risk preference, and the determining of N product sets corresponding to the N characteristic fields one by one includes: For a second field in the N characteristic fields, determining a risk attribute field associated with the second field in a preset product attribute library through a preset natural language processing model; the product attribute library includes a plurality of risk attribute fields, and the risk preference represented by the second field is the same as the risk attribute represented by the risk attribute field associated with the second field; Querying the risk attribute field associated with the second field in the product attribute library to determine at least one product corresponding to the second field; the product attribute library stores a mapping relationship between the risk attribute field and the product; Based on the at least one product corresponding to the second field, a product set corresponding to the second field is generated.

5. The method according to claim 1, It is characterized in that The N characteristic fields include a third field representing a product budget, and the determining of N product sets corresponding to the N characteristic fields one-to-one includes: For a third field in the N characteristic fields, a budget attribute field associated with the third field in a preset product attribute library is determined by a preset natural language processing model; the product attribute library includes a plurality of budget attribute fields, and the product budget represented by the third field is the same as the budget attribute represented by the budget attribute field associated with the third field; Querying the budget attribute field associated with the third field in the product attribute library to determine at least one product corresponding to the third field; the product attribute library stores a mapping relationship between the budget attribute field and the product; Based on the at least one product corresponding to the third field, a product set corresponding to the third field is generated.

6. The method according to claim 1, It is characterized in that The determining the target product based on the N product sets includes: Determine the products included in each of the N product sets; The products included in each of the product sets are determined as target products.

7. The method according to any one of claims 1 to 6, It is characterized in that The pushing the target product to the target user includes: Searching for the target product in a preset product knowledge base; the product knowledge base stores a mapping relationship between products and product information; Determine the product information that has a mapping relationship with the target product as the target product information; Converting the target product information into natural language text through a preset natural language processing model; The natural language text is pushed to the target user.

8. A product recommendation device, It is characterized in that include: An acquisition module, used to acquire text data of a conversation with a target user; A processing module, used for performing natural language processing on the text data to obtain N feature fields; The feature field is used to represent the product intention of the target user, and N is a positive integer; A first determining module is used to determine N product sets corresponding to the N characteristic fields one by one, each of the product sets including at least one product; A second determination module, configured to determine a target product based on the N product sets; A push module is used to push the target product to the target user.

9. A computer device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the product recommendation method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the product recommendation method according to any one of claims 1 to 7 are implemented.

Images