Information generation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an information generation method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining first information in response to an operation of triggering dialogue information generation for a to-be-recommended object, the first information comprises an identifier of a to-be-recommended object, an industry category to which the to-be-recommended object belongs and an external information acquisition channel, and generating basic introduction information of the to-be-recommended object according to the identifier of the to-be-recommended object, the external information acquisition channel and a first information generation model, generating a user demand strategy according to the industry category to which the to-be-recommended object belongs, a preset demand strategy library, the basic introduction information of the to-be-recommended object and a second information generation model, and generating field opening white information according to the identifier of the to-be-recommended object, the basic introduction information of the to-be-recommended object and a third information generation model, and displaying dialogue information including the basic introduction information of the to-be-recommended object, the open scene white information and the user demand strategy on a current interface.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to an information generation method, device, equipment and storage medium. Background Art

[0002] At present, most sales companies operate by manual telephone sales. Before telephone sales personnel communicate with customers, they need to understand the customers in advance and prepare corresponding sales pitches. Telephone sales personnel face a large number of customers every day, and need to spend a lot of time to understand and analyze the basic information of different customers and prepare corresponding sales pitches. The preparation time is long, and the quality of the sales pitch depends on the sales personnel's ability and experience.

[0003] How to generate high-quality customer service scripts and reduce the time and labor costs for preparing customer service scripts is an urgent problem that needs to be solved. Summary of the invention

[0004] The embodiments of the present application provide an information generation method, apparatus, device and storage medium, which can automatically generate dialogue information for a to-be-recommended object based on the information of the to-be-recommended object, reduce the preparation time and labor cost of the dialogue information, and improve the quality of the dialogue information.

[0005] In a first aspect, an embodiment of the present application provides an information generation method, comprising:

[0006] In response to an operation triggering generation of dialog information for a to-be-recommended object, first information is acquired, the first information including an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel;

[0007] Generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model;

[0008] Generate a user demand strategy according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended and a second information generation model;

[0009] Generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model;

[0010] The dialogue information is displayed on the current interface, wherein the dialogue information includes basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

[0011] In one embodiment, generating basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model includes:

[0012] Using the identifier of the object to be recommended as a keyword, searching using the external information acquisition channel to obtain first introduction information of the object to be recommended;

[0013] The first introduction information of the object to be recommended is input into the first information generation model, and the basic introduction information of the object to be recommended is output.

[0014] In one embodiment, if the industry category to which the object to be recommended belongs in the first information is empty, the method further includes:

[0015] According to the identifier of the object to be recommended and the preset information acquisition channel, determining the industry category of the identifier of the object to be recommended in the preset information acquisition channel;

[0016] The industry category to which the object to be recommended belongs is determined according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

[0017] In one embodiment, the determining, according to the identifier of the object to be recommended and the preset information acquisition channel, the industry category of the identifier of the object to be recommended in the preset information acquisition channel includes:

[0018] The identifier of the object to be recommended is used as a keyword, and the industry category search is performed using the preset information acquisition channel to obtain the industry category of the identifier of the object to be recommended in the preset information acquisition channel.

[0019] In one embodiment, determining the industry category to which the object to be recommended belongs according to the industry category of the identifier of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library includes:

[0020] The information generation model takes the industry category of the identification of the object to be recommended in the preset information acquisition channel and the internal industry classification library as inputs, and outputs the industry category to which the object to be recommended belongs. The information generation model is used to map the industry category of the identification of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library, so as to obtain the industry category to which the object to be recommended belongs.

[0021] In one embodiment, the generating of the user demand strategy according to the industry category to which the object to be recommended belongs, the preset demand strategy library, the basic introduction information of the object to be recommended and the second information generation model includes:

[0022] According to the industry category to which the object to be recommended belongs, N demand strategies are matched from the demand strategy library, where N is a positive integer;

[0023] Inputting the basic introduction information of the object to be recommended and the N demand strategies into the second information generation model, and outputting M demand strategies, where M is a preset positive integer;

[0024] The M demand strategies are determined as the user demand strategies.

[0025] In one embodiment, the user demand strategy includes at least one of a scenario name, an industry, a business scenario, a scenario priority level, an applicable position, a scenario pain point, and an implementation effect, and the industry includes a multi-level division of industries.

[0026] In one embodiment, generating the opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model includes:

[0027] Inputting the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and outputting the opening remarks information;

[0028] in:

[0029] The opening remarks information includes at least one of the following: a title, self-introduction information, historical consultation information, and inquiry demand information for the object to be recommended;

[0030] The title is determined according to the contact information in the basic introduction information of the object to be recommended.

[0031] In one embodiment, the first information further includes a channel and a method for sending the object to be recommended, and the method further includes:

[0032] Put the first information into a queue;

[0033] Determining the priority of the first information according to the delivery channel and delivery method of the object to be recommended;

[0034] The first information is dequeued according to the priority of the first information, so as to generate dialogue information for the object to be recommended.

[0035] In one embodiment, the dialog information displayed on the current interface includes basic introduction information of the recommended object, the opening remarks information and the user demand strategy, including:

[0036] The basic introduction information of the recommended object, the opening remarks information and the user demand strategy are combined into the dialogue information according to a preset format;

[0037] The dialog information is displayed at a preset position on the current interface.

[0038] In a second aspect, an embodiment of the present application provides an information generating device, including:

[0039] An acquisition module, configured to acquire first information in response to an operation triggering generation of dialog information for a to-be-recommended object, wherein the first information includes an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel;

[0040] A processing module, configured to generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model;

[0041] The processing module is also used to: generate a user demand strategy according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended and a second information generation model;

[0042] The processing module is further used to: generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model;

[0043] The display module is used to display the dialogue information on the current interface, wherein the dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

[0044] In one embodiment, the processing module is used to:

[0045] Using the identifier of the object to be recommended as a keyword, searching using the external information acquisition channel to obtain first introduction information of the object to be recommended;

[0046] The first introduction information of the object to be recommended is input into the first information generation model, and the basic introduction information of the object to be recommended is output.

[0047] In one embodiment, if the industry category to which the object to be recommended belongs in the first information is empty, the processing module is further configured to:

[0048] According to the identifier of the object to be recommended and the preset information acquisition channel, determining the industry category of the identifier of the object to be recommended in the preset information acquisition channel;

[0049] The industry category to which the object to be recommended belongs is determined according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

[0050] In one embodiment, the processing module is specifically used for:

[0051] The identifier of the object to be recommended is used as a keyword, and the industry category search is performed using the preset information acquisition channel to obtain the industry category of the identifier of the object to be recommended in the preset information acquisition channel.

[0052] In one embodiment, the processing module is specifically used for:

[0053] The information generation model takes the industry category of the identification of the object to be recommended in the preset information acquisition channel and the internal industry classification library as inputs, and outputs the industry category to which the object to be recommended belongs. The information generation model is used to map the industry category of the identification of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library, so as to obtain the industry category to which the object to be recommended belongs.

[0054] In one embodiment, the processing module is used to: match N demand strategies from the demand strategy library according to the industry category to which the object to be recommended belongs, where N is a positive integer;

[0055] Inputting the basic introduction information of the object to be recommended and the N demand strategies into the second information generation model, and outputting M demand strategies, where M is a preset positive integer;

[0056] The M demand strategies are determined as the user demand strategies.

[0057] In one embodiment, the user demand strategy includes at least one of a scenario name, an industry, a business scenario, a scenario priority level, an applicable position, a scenario pain point, and an implementation effect, and the industry includes a multi-level division of industries.

[0058] In one embodiment, the processing module is used to: input the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and output the opening remarks information;

[0059] in:

[0060] The opening remarks information includes at least one of the following: a title, self-introduction information, historical consultation information, and inquiry demand information for the object to be recommended;

[0061] The title is determined according to the contact information in the basic introduction information of the object to be recommended.

[0062] In one embodiment, the first information further includes a channel and a method for sending the object to be recommended, and the processing module is further configured to:

[0063] Put the first information into a queue;

[0064] Determining the priority of the first information according to the delivery channel and delivery method of the object to be recommended;

[0065] The first information is dequeued according to the priority of the first information, so as to generate dialogue information for the object to be recommended.

[0066] In one embodiment, the display module is used to:

[0067] The basic introduction information of the recommended object, the opening remarks information and the user demand strategy are combined into the dialogue information according to a preset format;

[0068] The dialog information is displayed at a preset position on the current interface.

[0069] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory, and executing the method in the first aspect or its various implementations.

[0070] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program enables a computer to execute the method in the first aspect or its various implementations.

[0071] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer program instructions, which enable a computer to execute a method as in the first aspect or its various implementations.

[0072] In summary, in the embodiment of the present application, by responding to the operation of triggering the generation of dialogue information for the object to be recommended, the first information is obtained, the first information includes the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel, then the basic introduction information of the object to be recommended is generated according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model, then the user demand strategy is generated according to the industry category to which the object to be recommended belongs, the pre-set demand strategy library, the basic introduction information of the object to be recommended and the second information generation model, and the opening remarks information is generated according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model, and the dialogue information is displayed on the current interface, the dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy. By using the information generation model, the dialogue information including the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy is automatically generated based on the information of the object to be recommended, thereby realizing the automatic generation of dialogue information for the object to be recommended according to the information of the object to be recommended, which can reduce the preparation time and labor cost of the dialogue information and improve the quality of the dialogue information. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 A schematic diagram of an application scenario of an information generation method provided in an embodiment of the present application;

[0075] Figure 2 A flowchart of an information generation method provided in an embodiment of the present application;

[0076] Figure 3 A flowchart of an information generation method provided in an embodiment of the present application;

[0077] Figure 4 A schematic diagram of a dialogue information generation interface provided in an embodiment of the present application;

[0078] Figure 5 A schematic diagram of a dialogue information generation interface provided in an embodiment of the present application;

[0079] Figure 6 A schematic diagram of the structure of an information generating device provided in an embodiment of the present application;

[0080] Figure 7 It is a schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0082] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes 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.

[0083] Before introducing the technical solution of this application, the following is an introduction to the relevant knowledge of this application:

[0084] 1. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that the machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level technology and software-level technology. Basic artificial intelligence technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technology mainly includes several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The technical solutions provided in the embodiments of this application mainly involve natural language processing technology and machine learning / deep learning in artificial intelligence.

[0085] 2. Large Language Model (LLM) is a deep learning model trained on massive text data. It can generate natural language text, deeply understand the meaning of text, and handle a variety of natural language tasks, such as text classification, question answering, dialogue, text summarization, translation, etc. The core principle of the large language model is based on neural networks, such as the Transformer model. Large language models are usually pre-trained on a large amount of text data to learn the basic laws, grammatical structures, semantic information, etc. of the language, and can capture the rich characteristics of the language.

[0086] In the related technology, a lot of time is needed to manually understand and analyze the basic information of different customers and prepare corresponding sales talk. The preparation time is long, and the quality of the sales talk depends on the ability and experience of the salesperson.

[0087] In order to solve this technical problem, in the embodiment of the present application, by using an information generation model, based on the information of the object to be recommended (including the identification of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel), the dialogue information is automatically generated, and the dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information, and the user demand strategy. The dialogue information for the object to be recommended is automatically generated based on the information of the object to be recommended, which can reduce the preparation time and labor cost of the dialogue information and improve the quality of the dialogue information.

[0088] It should be understood that the technical solution of the present application can be applied to the following scenarios, but is not limited to:

[0089] For example, Figure 1 A schematic diagram of an application scenario of an information generation method provided in an embodiment of the present application, such as Figure 1 As shown, the application scenario involves a terminal device 110 and a server 120 , and the terminal device 110 can communicate with the server 120 .

[0090] In some possible implementations, Figure 1 The application scenarios shown may also include: base stations, core network side equipment, etc. In addition, Figure 1 One terminal device and one server are shown as an example, but other numbers of terminal devices and servers may actually be included, and the embodiments of the present application do not limit this.

[0091] In some possible implementations, Figure 1The server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This embodiment of the application does not limit this.

[0092] In some possible implementations, such as Figure 1 The terminal device 110 shown may be installed with an application client, and when the application client runs in the terminal device, data can be exchanged with the server 120. For example, the client here may specifically include: a car client, a smart home client, a game client, a multimedia client (such as a video client), a social client, and an information client (such as a news client).

[0093] Optionally, in the embodiment of the present application, the terminal device 110 may be a device with rich human-computer interaction modes, the ability to access the Internet, usually equipped with various operating systems, and having strong processing capabilities. The terminal device 110 may be a smart phone, a smart TV, a tablet computer, a car terminal, etc., but is not limited thereto.

[0094] In one achievable manner, the server 120 and the terminal device 110 may execute the information generation method provided in the embodiment of the present application in an interactive manner, or the information generation method provided in the embodiment of the present application may be executed by the terminal device 110.

[0095] During the information generation model training phase, the server 120 or the terminal device 110 uses the training method provided in the embodiment of the present application to train and obtain the information generation model.

[0096] In the information generation stage, in an achievable manner, the user can trigger the operation of generating dialogue information for the object to be recommended through the client, browser client or instant messaging client installed in the terminal device 110. In response to the operation of triggering the generation of dialogue information for the object to be recommended, the terminal device obtains the first information, which includes the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel. Then, the terminal device generates basic introduction information of the object to be recommended based on the identifier of the object to be recommended, the external information acquisition channel and the first information generation model, generates user demand strategy based on the industry category to which the object to be recommended belongs, the pre-set demand strategy library, the basic introduction information of the object to be recommended and the second information generation model, generates opening remarks information based on the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model, and then displays the dialogue information on the current interface. The dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

[0097] In another achievable manner, the information generation method provided in the embodiment of the present application can also be interactively executed between the terminal device 110 and the server 120. For example, the user can trigger the operation of generating the dialogue information for the object to be recommended through the client, browser client or instant messaging client installed in the terminal device 110, and the terminal device 110 obtains the first information from the server 120, and the first information includes the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel. Then, the terminal device 110 generates the basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model, generates the user demand strategy according to the industry category to which the object to be recommended belongs, the pre-set demand strategy library, the basic introduction information of the object to be recommended and the second information generation model, generates the opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model, and then displays the dialogue information on the current interface, and the dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

[0098] It should be noted that the training process of the information generation model and the information generation process can be completed in the server or in the terminal device. Optionally, the model file (model file) trained in the server can be transplanted to the terminal device, and the terminal device executes the above process to generate dialogue information.

[0099] The information generation method provided in the embodiment of the present application can be applied to scenarios where telephone sales personnel need to spend a lot of time understanding and analyzing the basic information of different customers and preparing corresponding sales pitches when communicating with a large number of customers. It can also be applied to other scenarios, and this embodiment does not limit this.

[0100] The technical solution of this application will be described in detail below:

[0101] Figure 2 A flowchart of an information generation method provided in an embodiment of the present application, the method can be performed as follows Figure 1 The terminal device 110 shown executes, but is not limited to, Figure 2 As shown, the method may include the following steps:

[0102] S101. In response to an operation triggering generation of dialog information for a to-be-recommended object, first information is obtained, where the first information includes an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel.

[0103] Specifically, in one embodiment, the dialogue information may be customer speech information. For example, in the dialogue information preparation scenario, the user needs to prepare dialogue information before communicating with the customer. The user may trigger the operation of generating dialogue information for the object to be recommended. The operation may be, for example, opening the dialogue information generation interface. Selecting the object to be recommended is the operation of triggering the generation of dialogue information for the object to be recommended. It may also be triggered in other ways, which is not limited in this embodiment. In response to the operation of triggering the generation of dialogue information for the object to be recommended, the terminal device obtains the first information. The first information may be information pre-stored by the terminal device, which the terminal device directly obtains from the memory, or the terminal device obtains the first information from the server. The first information may be information collected and stored in advance, which is collected and stored in advance in the terminal device or the server for different objects to be recommended. In this embodiment, in the dialogue information preparation scenario, the object to be recommended may be an object to be sold or an object to be cooperated with, for example, an object that a telephone salesperson sells to a customer. The object to be sold may be an item, a physical product, a software product, or a hardware product, etc.

[0104] Among them, the first information is the relevant information of the object to be recommended. The first information may include the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel. Taking the object to be recommended as a company as an example, the identifier of the object to be recommended may be the company name, the industry category to which the object to be recommended belongs may be the industry category to which the company belongs, and the external information acquisition channel may be an information acquisition channel that can search for the relevant information of the company. The external information acquisition channel may be, for example, a professional enterprise information query tool or a data platform that can query enterprise information, or an application with enterprise information query capabilities. Optionally, the first information may also include the contact information of the object to be recommended, the distribution channel and distribution method of the object to be recommended, wherein the distribution channel may be any one of the official website, customer service, delivery, and referral, and the distribution method may be automatic allocation or non-automatic allocation.

[0105] Optionally, in an implementable manner, when the corresponding first information is collected and stored in advance for different objects to be recommended, it is also possible to use external information acquisition channels to search from external information acquisition channels according to the identifier of the object to be recommended as a keyword to obtain the industry category of the object to be recommended and the contact information of the object to be recommended in the first information of the object to be recommended. Specifically, when multiple pieces of information are searched, the final information can be selected by relevance, for example, one or more pieces of information with the greatest relevance among the multiple pieces of information searched are determined as the first information of the object to be recommended.

[0106] S102: Generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model.

[0107] Specifically, taking the object to be recommended as a company as an example, the basic introduction information of the object to be recommended can be the basic information of the company, wherein the first information generation model is a pre-trained model, and the first information generation model can be a large language model. After obtaining the first information, the basic introduction information of the object to be recommended can be generated by the first information generation model according to the identification of the object to be recommended and the external information acquisition channel.

[0108] In an practicable manner, in S102, basic introduction information of the object to be recommended is generated according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model, which may be:

[0109] S1021. Using the identifier of the object to be recommended as a keyword, use an external information acquisition channel to search and obtain the first introduction information of the object to be recommended.

[0110] S1022. Input the first introduction information of the object to be recommended into the first information generation model, and output the basic introduction information of the object to be recommended.

[0111] Specifically, there can be one or more external information acquisition channels. Compared with using one information acquisition channel, the basic introduction information obtained by using multiple information acquisition channels is more accurate and comprehensive. When there are multiple external information acquisition channels, taking two information acquisition channels as an example, the identifier of the object to be recommended is used as the keyword, and the first information acquisition channel is used to search to obtain the first introduction information of the object to be recommended. The identifier of the object to be recommended is used as the keyword, and the second information acquisition channel is used to search to obtain the second introduction information of the object to be recommended. The first introduction information and the second introduction information of the object to be recommended are input into the first information generation model, and the first information generation model generates and outputs the basic introduction information of the object to be recommended based on the first introduction information and the second introduction information.

[0112] Specifically, there is a situation where the industry category to which the object to be recommended belongs is not included in the first information. In an implementable manner, if the industry category to which the object to be recommended belongs in the first information is empty, that is, there is no information on the industry category, the method of this embodiment may further include:

[0113] S106: Determine the industry category of the identifier of the object to be recommended in the preset information acquisition channel according to the identifier of the object to be recommended and the preset information acquisition channel.

[0114] Specifically, the preset information acquisition channel can be a professional enterprise information query tool, and the information generation model can be a pre-trained large language model. According to the identifier of the object to be recommended and the preset information acquisition channel, the industry category of the identifier of the object to be recommended in the preset information acquisition channel can be determined. Industry categories include business services, e-commerce and life services, retail and services, etc.

[0115] S107: Determine the industry category to which the object to be recommended belongs according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

[0116] Specifically, in one embodiment, the internal industry classification library is obtained according to the industry and sales strategy. The internal industry classification library may be an industry classification library that is pre-divided according to the industry and sales strategy, which is different from the industry classification in the preset information acquisition channel. It may be an industry classification under two sets of division methods. For example, in the preset information acquisition channel, the industry category to which a company belongs is business services-organization management services-other organization management services. In the internal industry classification library, the industry category to which the company belongs is mass consumption, retail and service industry or catering industry.

[0117] Optionally, in an implementable manner, S106 may specifically be:

[0118] S1061. Using the identifier of the object to be recommended as a keyword, use a preset information acquisition channel to search for industry categories, and obtain the industry categories of the identifier of the object to be recommended in the preset information acquisition channel.

[0119] Optionally, in an implementable manner, S107 may specifically be:

[0120] S1071. Take the industry category of the identifier of the object to be recommended in the preset information acquisition channel and the internal industry classification library as inputs of the information generation model, and output the industry category to which the object to be recommended belongs. The information generation model is used to map the industry category of the identifier of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library, and obtain the industry category to which the object to be recommended belongs.

[0121] Specifically, the industry category of the identification of the object to be recommended in the preset information acquisition channel and the internal industry classification library are input into the information generation model, and the information generation model maps the industry category of the identification of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library. For example, the internal industry classification library includes 10 industry categories, and the information generation model maps the industry category of the identification of the object to be recommended in the preset information acquisition channel to one of the 10 industry categories. The obtained industry category is the industry category to which the object to be recommended belongs.

[0122] Optionally, the information generation model, the first information generation model, the second information generation model described below, and the third information generation model in the embodiments of the present application can all be large language models, for example, a transform model based on the prompt paradigm, or a model using other machine learning algorithms, such as a hidden Markov model (HMM), etc.

[0123] S103: Generate a user demand strategy based on the industry category to which the recommended object belongs, a preset demand strategy library, basic introduction information of the recommended object and a second information generation model.

[0124] Specifically, the user demand strategy includes information for exploring possible customer demand points or industry pain points. The pre-set demand strategy library includes demand strategies corresponding to different industries.

[0125] Optionally, in an implementable manner, in S103, a user demand strategy is generated according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended, and a second information generation model, which may be:

[0126] S1031. According to the industry category to which the object to be recommended belongs, N demand strategies are matched from the demand strategy library, where N is a positive integer.

[0127] Specifically, the demand strategy library includes demand strategies corresponding to different industries, and each industry corresponds to at least one demand strategy. According to the industry category to which the object to be recommended belongs, N demand strategies corresponding to the industry category to which the object to be recommended belongs can be queried from the demand strategy library.

[0128] S1032. Input the basic introduction information of the object to be recommended and N demand strategies into the second information generation model, and output M demand strategies, where M is a preset positive integer.

[0129] Specifically, M is set to 3, for example, and after the basic introduction information of the object to be recommended and N demand strategies are input into the second information generation model, the second information generation model outputs M demand strategies.

[0130] S1033. Determine the M demand strategies as user demand strategies.

[0131] Optionally, the user demand strategy includes at least one of the scenario name, industry, business scenario, scenario priority, applicable position, scenario pain point, and implementation effect, and the industry includes multi-level industries. For example, the industry includes primary industries, secondary industries, and tertiary industries.

[0132] S104: Generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model.

[0133] Specifically, in one practicable manner, S104 may specifically be:

[0134] S1041. Input the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and output the opening remarks information.

[0135] Wherein: the opening remarks information includes at least one of the following: title, self-introduction information, historical consultation information and inquiry demand information for the object to be recommended; the title is determined according to the contact information in the basic introduction information of the object to be recommended.

[0136] As an example, taking the object to be recommended as AA, for example, the generated opening remarks are "Hello, Mr. X (XXX), I am an official staff member of AA. You have consulted relevant information through our customer service channels today. May I ask which functions of AA would you like to know more about?" "Mr. X" is a title, and the title is determined according to the contact information in the basic introduction information of the object to be recommended, "I am an official staff member of AA" is the self-introduction information, and "You have consulted relevant information through our customer service channels today" is the historical consultation information, or it can be generated based on the historical consultation information, and "May I ask which functions of AA would you like to know more about" is the inquiry demand information for the object to be recommended. Optionally, in one embodiment, the title and self-introduction information can be fixed settings, and the historical consultation information and the inquiry demand information for the object to be recommended can be generated by a third information generation model.

[0137] S105. Displaying the dialogue information on the current interface, the dialogue information includes basic introduction information of the recommended object, opening remarks information and user demand strategy.

[0138] Optionally, as an implementable manner, S105 may specifically be:

[0139] S1051. The basic introduction information, opening remarks information and user demand strategy of the recommended object are combined into dialogue information according to a preset format.

[0140] S1052: Display the dialog information at a preset position of the current interface.

[0141] Optionally, in an implementable manner, the first information further includes a delivery channel and delivery method of the object to be recommended. The method of this embodiment may further include:

[0142] S108: Put the first information into a queue.

[0143] S109: Determine the priority of the first information according to the distribution channel and distribution method of the object to be recommended.

[0144] The distribution channel of the recommended object may be any one of the official website, customer service, delivery and referral, and the distribution method may be automatic allocation or non-automatic allocation. The priority of non-automatic allocation is higher than the priority of automatic allocation. In one embodiment, for example, the priority may be determined first according to the distribution method, and if the priority cannot be determined according to the distribution method, the priority is determined according to the distribution channel.

[0145] S110 , the first information is dequeued according to the priority of the first information, so as to generate dialogue information for the object to be recommended.

[0146] In this embodiment, by determining the priority according to the entry and then exiting the queue, the dialogue information for multiple objects to be recommended can be generated simultaneously according to the priority.

[0147] The information generation method provided in this embodiment obtains first information in response to an operation that triggers the generation of dialogue information for the object to be recommended, the first information includes the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and the external information acquisition channel, then generates basic introduction information of the object to be recommended based on the identifier of the object to be recommended, the external information acquisition channel, and the first information generation model, then generates user demand strategy based on the industry category to which the object to be recommended belongs, the preset demand strategy library, the basic introduction information of the object to be recommended, and the second information generation model, generates opening remarks information based on the identifier of the object to be recommended, the basic introduction information of the object to be recommended, and the third information generation model, and displays dialogue information on the current interface, the dialogue information including the basic introduction information of the object to be recommended, the opening remarks information, and the user demand strategy. By using the information generation model, dialogue information including the basic introduction information of the object to be recommended, the opening remarks information, and the user demand strategy are automatically generated based on the information of the object to be recommended, thereby realizing the automatic generation of dialogue information for the object to be recommended based on the information of the object to be recommended, which can reduce the preparation time and labor cost of the dialogue information and improve the quality of the dialogue information.

[0148] The technical solution of the embodiment of the present application is described in detail below in conjunction with a specific embodiment.

[0149] Figure 3A flowchart of an information generation method provided in an embodiment of the present application, the method can be performed as follows Figure 1 The terminal device 110 shown executes, but is not limited to, Figure 3 As shown, the method may include the following steps:

[0150] S201. In response to an operation that triggers generation of dialog information for a to-be-recommended object, first information is obtained, where the first information includes an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel.

[0151] In this embodiment, in the dialogue information preparation scenario, the object to be recommended may be an object to be sold or an object to be cooperated with, for example, an object that a telephone salesperson sells to a customer. The object to be sold may be an item, a physical product, a software product, a hardware product, or the like.

[0152] In this embodiment, the first information also includes the sending channel and sending method of the object to be recommended.

[0153] S202: Put the first information into a queue.

[0154] S203: Determine the priority of the first information according to the delivery channel and delivery method of the object to be recommended.

[0155] The distribution channel of the recommended object may be any one of the official website, customer service, delivery and referral, and the distribution method may be automatic allocation or non-automatic allocation. The priority of non-automatic allocation is higher than the priority of automatic allocation. In one embodiment, for example, the priority may be determined first according to the distribution method, and if the priority cannot be determined according to the distribution method, the priority is determined according to the distribution channel.

[0156] S204: The first information is dequeued according to the priority of the first information, so as to generate dialogue information for the object to be recommended.

[0157] In this embodiment, by determining the priority according to the entry and then exiting the queue, the dialogue information for multiple objects to be recommended can be generated simultaneously according to the priority.

[0158] S205: Generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model.

[0159] In an practicable manner, in S205, basic introduction information of the object to be recommended is generated according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model, which may be:

[0160] S2051. Using the identifier of the object to be recommended as a keyword, use an external information acquisition channel to search and obtain the first introduction information of the object to be recommended.

[0161] S2052: Input the first introduction information of the object to be recommended into the first information generation model, and output the basic introduction information of the object to be recommended.

[0162] Specifically, there is a situation where the industry category to which the object to be recommended belongs is not included in the first information. In an implementable manner, if the industry category to which the object to be recommended belongs in the first information is empty, that is, there is no information on the industry category, the method of this embodiment may further include:

[0163] S206: Determine the industry category of the identifier of the object to be recommended in the preset information acquisition channel according to the identifier of the object to be recommended and the preset information acquisition channel.

[0164] Specifically, the preset information acquisition channel can be a professional enterprise information query tool, and the information generation model can be a pre-trained large language model. According to the identifier of the object to be recommended and the preset information acquisition channel, the industry category of the identifier of the object to be recommended in the preset information acquisition channel can be determined. Industry categories include business services, e-commerce and life services, retail and services, etc.

[0165] S207: Determine the industry category to which the object to be recommended belongs according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

[0166] Specifically, in one embodiment, the internal industry classification library is an industry classification library that is pre-divided according to industries and sales strategies, which is different from the industry classification in the preset information acquisition channel. It can be an industry classification under two sets of division methods. For example, in the preset information acquisition channel, the industry category to which a company belongs is business services-organization management services-other organization management services. In the internal industry classification library, the industry category to which the company belongs is mass consumption, retail and service industry or catering industry.

[0167] Optionally, the specific implementation of S206 may refer to the above S106, and the specific implementation of S207 may refer to the above S207, which will not be repeated here.

[0168] S208: Generate a user demand strategy based on the industry category to which the recommended object belongs, a preset demand strategy library, basic introduction information of the recommended object, and a second information generation model.

[0169] Specifically, the user demand strategy includes information for exploring possible customer demand points or industry pain points. The pre-set demand strategy library includes demand strategies corresponding to different industries.

[0170] Optionally, in an implementable manner, in S208, a user demand strategy is generated according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended, and a second information generation model, which may be:

[0171] S2081. According to the industry category to which the object to be recommended belongs, N demand strategies are matched from the demand strategy library, where N is a positive integer.

[0172] Specifically, the demand strategy library includes demand strategies corresponding to different industries, and each industry corresponds to at least one demand strategy. According to the industry category to which the object to be recommended belongs, N demand strategies corresponding to the industry category to which the object to be recommended belongs can be queried from the demand strategy library.

[0173] S2082. Input the basic introduction information of the recommended object and N demand strategies into the second information generation model, and output M demand strategies, where M is a preset positive integer.

[0174] Specifically, M is set to 3, for example, and after the basic introduction information of the object to be recommended and N demand strategies are input into the second information generation model, the second information generation model outputs M demand strategies.

[0175] S2083. Determine the M demand strategies as user demand strategies.

[0176] Optionally, the user demand strategy includes at least one of the scenario name, industry, business scenario, scenario priority, applicable position, scenario pain point, and implementation effect, and the industry includes multi-level industries. For example, the industry includes primary industries, secondary industries, and tertiary industries.

[0177] Figure 4 A schematic diagram of a dialogue information generation interface provided in an embodiment of the present application, such as Figure 4 As shown, taking AA as an example, the recommended object is e-commerce and life services-sales manager-live broadcast management, the first-level industry is the Internet and information technology, the second-level industry is e-commerce and life services, the business scenario is live broadcast management, the scenario priority level is level four, and the applicable positions include sales manager, operation manager and marketing manager. The generated user demand strategy includes 3 strategies, namely "1. Integrate the numerous business processes of XX e-commerce, and use AA to create a "business + team collaboration" dual-effect management platform to enable seamless connection between corporate office and XX e-commerce and achieve a response in seconds; 2. From video content production, live broadcast planning to real-time e-commerce data analysis, XXX will organize it for you to make data-driven decision-making more intuitive and faster; 3. Using AA, you can connect with the XX data platform to achieve efficient internal and external collaboration, allowing you to enjoy cutting-edge business management experience anytime, anywhere". The scenario pain points and implementation effects are as follows Figure 4 As shown in , it includes information corresponding to brand docking, layer-by-layer summary and real-time reporting.

[0178] Figure 5 A schematic diagram of a dialogue information generation interface provided in an embodiment of the present application, such as Figure 5 As shown, taking AA as an example, the recommended object is retail and service industry-store management, the first-level industry is mass consumption, the second-level industry is retail and service industry, the third-level industry is catering, the business scenario is store management, the scenario priority level is level five, and the applicable positions are to be selected. The generated user demand strategy is "In the store management of the retail and service industries, AA uses XXX to not only realize automated store task management and process distribution, but also ensure that each task is accurately communicated and executed. AA's approval and form functions completely digitize the supply chain process, so that everything from procurement needs to financial data settlement is tracked and managed in real time. The AA knowledge base and service desk have created a perfect learning and communication platform for store employees, enabling them to quickly master knowledge and service standards. In addition, for daily inspections and problem feedback of stores, AA provides a complete system to ensure that all problems are handled in a timely manner, ultimately bringing customers a unified and high-quality brand experience", the scenario pain points and implementation effects are shown as follows. Figure 5 as shown in .

[0179] S209: Generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model.

[0180] Specifically, in one practicable manner, S209 may specifically be:

[0181] S2091. Input the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and output the opening remarks information.

[0182] The opening remarks include at least one of the following: a title, self-introduction information, historical consultation information, and inquiry demand information for the recommended object. The title is determined based on the contact information in the basic introduction information of the recommended object.

[0183] S210: Displaying the dialogue information on the current interface, the dialogue information including basic introduction information of the recommended object, opening remarks information and user demand strategy.

[0184] Optionally, as an implementable manner, S210 may specifically be:

[0185] S2101. The basic introduction information, opening remarks information and user demand strategy of the recommended object are combined into dialogue information according to a preset format.

[0186] S2102. Displaying the dialog information at a preset position of the current interface.

[0187] The information generation method provided in this embodiment realizes automatic generation of dialogue information for the object to be recommended based on the information of the object to be recommended, which can reduce the preparation time and labor cost of the dialogue information and improve the quality of the dialogue information.

[0188] Figure 6 A schematic diagram of the structure of an information generating device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the information generating device may include: an acquisition module 11, a processing module 12 and a display module 13.

[0189] The acquisition module 11 is used to obtain first information in response to an operation that triggers the generation of dialogue information for the object to be recommended, the first information including the identifier of the object to be recommended, the industry category to which the object to be recommended belongs, and an external information acquisition channel;

[0190] The processing module 12 is used to generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model;

[0191] The processing module 12 is also used to: generate a user demand strategy according to the industry category to which the recommended object belongs, the preset demand strategy library, the basic introduction information of the recommended object and the second information generation model;

[0192] The processing module 12 is also used to: generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model;

[0193] The display module 13 is used to display the dialogue information on the current interface, and the dialogue information includes basic introduction information of the object to be recommended, opening remarks information and user demand strategy.

[0194] In one embodiment, the processing module 12 is used to: use the identifier of the object to be recommended as a keyword and use an external information acquisition channel to search and obtain the first introduction information of the object to be recommended;

[0195] The first introduction information of the object to be recommended is input into the first information generation model, and the basic introduction information of the object to be recommended is output.

[0196] In one embodiment, if the industry category to which the recommended object belongs in the first information is empty, the processing module 12 is further configured to:

[0197] According to the identifier of the object to be recommended and the preset information acquisition channel, determine the industry category of the identifier of the object to be recommended in the preset information acquisition channel;

[0198] The industry category to which the object to be recommended belongs is determined according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

[0199] In one embodiment, the processing module 12 is specifically used for:

[0200] The identifier of the object to be recommended is used as a keyword, and the industry category search is performed using a preset information acquisition channel to obtain the industry category of the identifier of the object to be recommended in the preset information acquisition channel.

[0201] In one embodiment, the processing module 12 is specifically used for:

[0202] The information generation model takes the industry category of the identification of the object to be recommended in the preset information acquisition channel and the internal industry classification library as the input, and outputs the industry category to which the object to be recommended belongs. The information generation model is used to map the industry category of the identification of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library, and obtain the industry category to which the object to be recommended belongs.

[0203] In one embodiment, the processing module 12 is used to: match N demand strategies from the demand strategy library according to the industry category to which the recommended object belongs, where N is a positive integer;

[0204] Input the basic introduction information of the recommended object and N demand strategies into the second information generation model, and output M demand strategies, where M is a preset positive integer;

[0205] The M demand strategies are determined as user demand strategies.

[0206] In one embodiment, the user demand strategy includes at least one of a scenario name, industry, business scenario, scenario priority level, applicable positions, scenario pain points, and implementation effects, and the industry includes a multi-level division of industries.

[0207] In one embodiment, the processing module 12 is used to: input the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and output the opening remarks information.

[0208] The opening remarks include at least one of the following: a title, self-introduction information, historical consultation information, and inquiry information for the recommended object. The title is determined based on the contact information in the basic introduction information of the recommended object.

[0209] In one embodiment, the first information also includes a distribution channel and a distribution method of the recommended object, and the processing module 12 is further used to:

[0210] Put the first message into the queue;

[0211] Determine the priority of the first information according to the distribution channel and distribution method of the recommended object;

[0212] The first information is dequeued according to the priority of the first information, so as to generate the dialogue information for the object to be recommended.

[0213] In one embodiment, the display module 13 is used to:

[0214] The basic introduction information, opening remarks and user demand strategy of the recommended object are combined into dialogue information according to a preset format;

[0215] Display the dialog information at the preset position of the current interface.

[0216] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 6 The information generating device shown can execute Figure 2 The corresponding method embodiments, and the aforementioned and other operations and / or functions of each module in the information generating device are respectively to achieve Figure 2 For the sake of brevity, the corresponding processes in the corresponding method embodiments are not repeated here.

[0217] The information generation model training device of the embodiment of the present application is described above from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware encoding processor to execute, or a combination of hardware and software modules in the encoding processor to execute. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0218] Figure 7 is a schematic block diagram of an electronic device provided in an embodiment of the present application. The electronic device may be a server in the above method embodiment.

[0219] like Figure 7 As shown, the electronic device may include:

[0220] The memory 210 and the processor 220, the memory 210 is used to store the computer program and transmit the program code to the processor 220. In other words, the processor 220 can call and run the computer program from the memory 210 to implement the method in the embodiment of the present application.

[0221] For example, the processor 220 may be configured to execute the above method embodiments according to instructions in the computer program.

[0222] In some embodiments of the present application, the processor 220 may include but is not limited to:

[0223] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0224] In some embodiments of the present application, the memory 210 includes but is not limited to:

[0225] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0226] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 210 and executed by the processor 220 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0227] like Figure 7 As shown, the electronic device may also include:

[0228] The transceiver 230 may be connected to the processor 220 or the memory 210 .

[0229] The processor 220 may control the transceiver 230 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 230 may include a transmitter and a receiver. The transceiver 230 may further include an antenna, and the number of antennas may be one or more.

[0230] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0231] The present application also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.

[0232] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.

[0233] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0234] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 devices or modules, which can be electrical, mechanical or other forms.

[0235] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0236] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for generating information, characterized in that: include: In response to an operation triggering generation of dialog information for a to-be-recommended object, first information is acquired, the first information including an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel; Generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model; Generate a user demand strategy according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended and a second information generation model; Generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model; The dialogue information is displayed on the current interface, wherein the dialogue information includes basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

2. The method according to claim 1, characterized in that The step of generating basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model includes: Using the identifier of the object to be recommended as a keyword, searching using the external information acquisition channel to obtain first introduction information of the object to be recommended; The first introduction information of the object to be recommended is input into the first information generation model, and the basic introduction information of the object to be recommended is output.

3. The method according to claim 1 or 2, characterized in that: If the industry category to which the recommended object belongs in the first information is empty, the method further includes: According to the identifier of the object to be recommended and the preset information acquisition channel, determining the industry category of the identifier of the object to be recommended in the preset information acquisition channel; The industry category to which the object to be recommended belongs is determined according to the industry category of the identification of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library.

4. The method according to claim 3, characterized in that: The step of determining the industry category of the identifier of the object to be recommended in the preset information acquisition channel according to the identifier of the object to be recommended and the preset information acquisition channel comprises: The identifier of the object to be recommended is used as a keyword, and the industry category search is performed using the preset information acquisition channel to obtain the industry category of the identifier of the object to be recommended in the preset information acquisition channel.

5. The method according to claim 3, characterized in that: The step of determining the industry category to which the object to be recommended belongs according to the industry category of the identifier of the object to be recommended in the preset information acquisition channel, the information generation model and the internal industry classification library includes: The information generation model takes the industry category of the identification of the object to be recommended in the preset information acquisition channel and the internal industry classification library as inputs, and outputs the industry category to which the object to be recommended belongs. The information generation model is used to map the industry category of the identification of the object to be recommended in the preset information acquisition channel to an industry category in the internal industry classification library, so as to obtain the industry category to which the object to be recommended belongs.

6. The method according to claim 1, characterized in that The generating of the user demand strategy according to the industry category to which the object to be recommended belongs, the preset demand strategy library, the basic introduction information of the object to be recommended and the second information generating model comprises: According to the industry category to which the object to be recommended belongs, N demand strategies are matched from the demand strategy library, where N is a positive integer; Inputting the basic introduction information of the object to be recommended and the N demand strategies into the second information generation model, and outputting M demand strategies, where M is a preset positive integer; The M demand strategies are determined as the user demand strategies.

7. The method according to claim 6, characterized in that The user demand strategy includes at least one of the scenario name, industry, business scenario, scenario priority level, applicable positions, scenario pain points and implementation effect, and the industry includes multi-level divided industries.

8. The method according to claim 1, characterized in that The step of generating the opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model includes: Inputting the identifier of the object to be recommended and the basic introduction information of the object to be recommended into the third information generation model, and outputting the opening remarks information; in: The opening remarks information includes at least one of the following: a title, self-introduction information, historical consultation information, or inquiry demand information for the object to be recommended; The title is determined according to the contact information in the basic introduction information of the object to be recommended.

9. The method according to claim 1, characterized in that: The first information also includes a distribution channel and a distribution method of the object to be recommended, and the method further includes: Put the first information into a queue; Determining the priority of the first information according to the delivery channel and delivery method of the object to be recommended; The first information is dequeued according to the priority of the first information, so as to generate dialogue information for the object to be recommended.

10. The method according to claim 1, characterized in that The dialog information is displayed on the current interface, and the dialog information includes basic introduction information of the recommended object, the opening remarks information and the user demand strategy, including: The basic introduction information of the recommended object, the opening remarks information and the user demand strategy are combined into the dialogue information according to a preset format; The dialog information is displayed at a preset position on the current interface.

11. An information generating device, characterized in that: include: An acquisition module, configured to acquire first information in response to an operation triggering generation of dialog information for a to-be-recommended object, wherein the first information includes an identifier of the to-be-recommended object, an industry category to which the to-be-recommended object belongs, and an external information acquisition channel; A processing module, configured to generate basic introduction information of the object to be recommended according to the identifier of the object to be recommended, the external information acquisition channel and the first information generation model; The processing module is also used to: generate a user demand strategy according to the industry category to which the object to be recommended belongs, a preset demand strategy library, basic introduction information of the object to be recommended and a second information generation model; The processing module is further used to: generate opening remarks information according to the identifier of the object to be recommended, the basic introduction information of the object to be recommended and the third information generation model; The display module is used to display the dialogue information on the current interface, wherein the dialogue information includes the basic introduction information of the object to be recommended, the opening remarks information and the user demand strategy.

12. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The invention comprises instructions which, when executed on a computer program, cause the computer to perform the method as claimed in any one of claims 1 to 10.

Images