Resource information recommendation method and device, storage medium and program product

Abstract

The embodiment of the invention provides a resource information recommendation method and device, a storage medium and a program product. In the embodiment of the invention, the AI resource information recommendation model is utilized, the first target resource configuration information is determined from various resource configuration information based on the potential multi-dimensional resource demand information of the first user and the recommendation condition of the resource configuration information, and the adaptive resource configuration information is quickly and accurately matched for the user; besides, the language style information of the first user can be analyzed based on the initial and deep portrait data of the first user, so that recommendation reason information and verbal skill information for recommending the first target resource configuration information to the first user are generated; the target service personnel can adopt the verbal skill provided by the verbal skill information to recommend the first target resource configuration information to the first user through the recommendation reason information, so that the persuasion of recommending the resource configuration information is improved, the first user is adapted from the language style, the acceptance of the user to the recommendation process is improved, and the conversion rate of the resource configuration information is improved.

Description

Technical Field

[0001] This application relates to the field of computer processing technologies, and in particular, to a method, device, storage medium, and program product for resource information recommendation. Background Art

[0002] With the development of the Internet industry, Internet services have become increasingly rich to meet the needs of different customers. Taking the platform services provided by a service platform as an example, the service platform can provide a variety of platform services, and the customer rights and interests included in different services are different. Currently, in the face of numerous service options, platform salespersons can rely on experience and intuition to recommend platform services suitable for customers. However, this traditional recommendation method lacks data support and personalized recommendation capabilities, making it difficult to quickly and accurately recommend the most suitable service for users. Moreover, the recommendation scripts used by salespersons to recommend services to users often also depend on their own experience accumulation, and the persuasion ability is not strong, thus affecting the conversion rate of platform services. Summary of the Invention

[0003] Multiple aspects of this application provide a method, device, storage medium, and program product for resource information recommendation, which are used to quickly and accurately match suitable resource configuration information for users, and generate recommendation reason information and script information adapted to the recommended resource configuration information, so as to recommend the resource configuration information to users with the script skills provided by the script information and the recommendation reason information, improving the persuasion of the recommended resource configuration information, and thus increasing the conversion rate of the resource configuration information.

[0004] The embodiment of the present application provides a resource information recommendation method, which is applied to a recommendation platform. The method includes: in response to a resource information recommendation request submitted by a target service personnel in a target service field, obtaining initial portrait data and depth portrait data of a first user, wherein the initial portrait data is obtained by performing a user portrait analysis based on the user information of the first user, and the depth portrait data is obtained by performing a user portrait analysis based on the conversation content between the target service personnel and the first user; performing a potential resource demand analysis on the first user based on the initial portrait data and the depth portrait data, and obtaining potential multi-dimensional resource demand information of the first user; inputting the initial portrait data, the depth portrait data, the multi-dimensional resource demand information and the resource configuration information and their recommendation conditions into an AI resource information recommendation model, and based on the multi-dimensional resource demand information and Recommendation conditions for resource configuration information, selecting the first target resource configuration information from a variety of resource configuration information and generating recommendation reason information for the first target resource configuration information; analyzing the language style information of the first user based on the initial portrait data and the deep portrait data, and generating speech information for recommending the first target resource configuration information to the first user with recommendation reason information based on the language style information; wherein the AI resource information recommendation model is obtained by fine-tuning the pre-trained model based on sample data of the target service field; sending the first target resource configuration information, the recommendation reason information and the speech information to the first terminal of the target service personnel, so that the target service personnel can use the speech information to recommend the first target resource configuration information to the first user with recommendation reason information through the communication channel between the first terminal and the second terminal of the first user.

[0005] An embodiment of the present application also provides an electronic device, comprising: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement each step in the above method.

[0006] An embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements each step of the above method.

[0007] An embodiment of the present application further provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the processor is enabled to implement each step in the above method.

[0008] In the embodiments of the present application, by using the AI resource information recommendation model, based on the recommendation conditions of the potential multi-dimensional resource requirements information and resource configuration information of the first user, the first target resource configuration information is determined from various resource configuration information, quickly and accurately matching the appropriate resource configuration information for the user; in addition, the language style information of the first user can be analyzed based on the initial and in-depth portrait data of the first user, and accordingly, the recommendation reason information and the conversation information for recommending the first target resource configuration information to the first user are generated. The target service personnel can use the conversation skills provided by the conversation information to recommend the first target resource configuration information to the first user with the recommendation reason information, improving the persuasiveness of the recommended resource configuration information, adapting to the first user in terms of language style, increasing the acceptance degree of the user for the recommendation process, and improving the conversion rate of the resource configuration information. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings: Figure 1 FIG. is a schematic structural diagram of a resource information recommendation system provided by an exemplary embodiment of the present application; Figure 2a FIG. is a schematic flowchart of a resource information recommendation method provided by an exemplary embodiment of the present application; Figure 2b FIG. is a schematic flowchart of another resource information recommendation method provided by another exemplary embodiment of the present application; Figure 2c FIG. is a schematic flowchart of yet another resource information recommendation method provided by yet another exemplary embodiment of the present application; Figure 2d FIG. is a schematic flowchart of a model training process provided by an exemplary embodiment of the present application; Figure 2e FIG. is a schematic flowchart of a resource information generation process provided by an exemplary embodiment of the present application; Figure 3 FIG. is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0011] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0012] Users who purchase resource configuration information can enjoy corresponding user rights and interests. Users can be B-end enterprises that provide services or products, or C-end users who need services or products. Taking posting as an example, B-end enterprises need to promote their services or products through posting, so the enterprise needs some posting rights to increase the exposure of the post, and thus needs to purchase resource configuration information to enjoy the corresponding posting rights and interests. Alternatively, C-end users need to purchase services or products, but have no purchasing experience and need the platform to recommend services or products that suit their needs, so they can purchase resource configuration information to enjoy the corresponding recommendation rights and interests; or users can post to seek services or products, then the user needs some posting rights to increase the exposure of the post, and thus needs to purchase resource configuration information to enjoy the corresponding posting rights and interests.

[0013] Currently, faced with a multitude of resource configuration information options, platform sales staff can rely on experience and intuition to recommend suitable resource configuration information to customers. However, this traditional recommendation method lacks data support and personalized recommendation capabilities, making it difficult to quickly and accurately recommend the most appropriate resource configuration information to users. Moreover, the sales staff's recommendation language for resource configuration information to users often depends on their own accumulated experience, and their persuasive ability is not strong, which affects the conversion rate of the platform's resource configuration information.

[0014] In response to the above technical problems, in an embodiment of the present application, an AI resource information recommendation model is utilized to determine the first target resource configuration information from a variety of resource configuration information based on the recommendation conditions of the first user's potential multi-dimensional resource demand information and resource configuration information, and quickly and accurately match the adapted resource configuration information for the user; in addition, the language style information of the first user can be analyzed based on the initial and deep portrait data of the first user, and recommendation reason information and speech information for recommending the first target resource configuration information to the first user are generated accordingly. The target service personnel can use the speech skills provided by the speech information to recommend the first target resource configuration information to the first user with the recommendation reason information, thereby improving the persuasiveness of the recommended resource configuration information, and also adapting the language style to the first user, thereby improving the user's acceptance of the recommendation process and improving the conversion rate of the resource configuration information.

[0015] The technical solutions provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0016] Figure 1 This is a schematic structural diagram of a resource information recommendation system provided for an exemplary embodiment of the present application. As Figure 1 shown, the resource information recommendation system includes: a recommendation platform 101 and a first terminal 102, and the recommendation platform 101 and the first terminal 102 can be communicatively connected. It should be noted that Figure 1 this is only an exemplary schematic diagram and does not limit the technical solution of the present application.

[0017] Among them, the first terminal is a terminal device used by target service personnel in the target field. The implementation form of the first terminal is not limited in this embodiment. For example, the first terminal can be a smart phone, a tablet computer, a notebook computer or a desktop computer, etc.; for another example, the first terminal can also be a smart wearable device, such as a smart watch, a smart bracelet, etc.; for still another example, the first terminal can also be various smart home appliances with a display screen, such as a smart TV, a smart large screen or a smart robot, etc. In addition, various software applications can be installed on the first terminal. The software application can be an independently running APP, a small program that depends on the APP to run, or a web page. This embodiment does not limit this. The software applications installed on the first terminal include but are not limited to: instant messaging applications and service applications. Among them, the instant messaging application refers to an application program that allows two or more people to exchange messages in real time through the network. It supports users to send text messages, pictures, videos, voice messages, file transfers, etc., and usually also provides voice and video call functions. The instant messaging application can be, for example, a conversation tool such as WeChat or Weibo. The service application is used to provide services or goods. The service application can be, for example, an application that provides special services such as a recruitment application, a house rental application, a shopping application, a car-hailing application, etc. or a comprehensive service application that provides various services and goods. This embodiment does not limit this. The service application can also include a conversation function, and the conversation function includes but is not limited to: customer service consultation service and call service. The customer service consultation service refers to the consultation service provided by the customer service of the application to the user and the consultation service can be carried out through the conversation interface. The call service refers to the function provided by the application to the user to call the enterprise that provides the service or goods. In addition, when the recommendation platform is implemented as a software application, it can be installed on the first terminal of the target service personnel or on other terminals outside the terminal used by the service personnel. This embodiment does not limit this.

[0018] The recommendation platform can store various resource configuration information of the target field and user information of multiple users. The users refer to registered users of other applications associated with the recommendation platform, such as users of service applications. Users can be B-end enterprises that provide services or goods, or C-end users who need services or goods. In an optional embodiment, the recommendation platform can be implemented as a software application, which can have high processing capabilities and can perform Figure 2a Each step of the relevant embodiment achieves the purpose of sending the resource configuration information matched for the user and its configuration content, recommendation reason information and speech information to the first terminal of the target service personnel, so that the target service personnel can use the speech skills provided by the speech information to recommend the resource configuration information to the user with the recommendation reason information. This embodiment does not limit the specific implementation form of the software application. The software application can be an independently running APP, a small program that depends on the APP to run, or a web page. In another optional embodiment, the recommendation platform can also be implemented as a server, which can perform the following operations: Figure 2a The steps of the relevant embodiments. This embodiment does not limit the specific implementation form of the server side implemented by the recommendation platform, and the server side can be a single physical server, a cloud server, or a server array.

[0019] Optionally, the resource information recommendation system further includes a second terminal 103. The second terminal can be a terminal device used by a B-end enterprise or a C-end user. For ease of description and distinction, it is referred to as the first user. This embodiment does not limit the specific implementation of the second terminal; please refer to the relevant description of the first terminal and will not be repeated here. The recommendation platform sends the resource configuration information matched for the first user, its configuration content, recommendation reason information, and speech information to the first terminal of the target service personnel, so that the target service personnel can recommend the resource configuration information to the first user through the communication channel between the first terminal and the second terminal of the first user, using the speech skills provided in the speech information and the recommendation reason information. The communication link can be a communication channel established between the first terminal and the second terminal, and the communication channel can be established based on the recommendation platform. For example, the recommendation platform establishes a communication channel between the first terminal and the second terminal in response to a call request from the target service personnel to call the first user. For another example, after the recommendation platform sends the resource configuration information, recommendation information, and speech information matched for the first user to the first terminal, within a preset time, the recommendation platform automatically initiates a double call to the first terminal and the second terminal to establish the communication channel between the first terminal and the second terminal.

[0020] Further optionally, the resource information recommendation system further includes: a service platform 104 (such as the service application in the above embodiment), where the service platform is used to provide various resource configuration information in the target service area and the corresponding rights and interests for each resource configuration information. Further, an enterprise providing services or goods can register as an enterprise member on the service platform, and a user in need of services or goods can register as a user member on the service platform. The service platform can also be communicatively connected to the recommendation platform to synchronize various resource configuration information in the target service area, the configuration content of each resource configuration information, the enterprise information of each enterprise, and the user information of each user to the recommendation platform, so that the recommendation platform can store these information and execute the steps related to Figure 2a the relevant embodiments. In the embodiments of the present application, the users mainly focused on are B-end enterprises.

[0021] In this embodiment, the above communication connection can be a wireless communication connection or a wired communication connection. The specific communication connection method to be used can be determined according to the implementation form of each component included in the resource information recommendation system. When the implementation form of the relevant component is a physical form (or entity form), either a wireless communication connection method or a wired communication connection method can be used. When the implementation form of the relevant component is a non-physical form (virtual form), a wireless communication connection method can be used. For the wireless communication connection method, optionally, the communication connection can be achieved through a mobile network. Correspondingly, the network mode of the mobile network can be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), 5G, WiMax, or any new network mode that will emerge in the future. Additionally, in the case where the relevant components are located in the same local area network, a wireless communication connection can also be achieved through Bluetooth, WiFi, infrared, zigbee, or NFC, etc.

[0022] It should be noted that Figure 2a the relevant embodiments can be described around the system architecture including a recommendation platform, a first terminal, a second terminal, and a service platform in the resource information recommendation system, but do not limit the technical solution of the present application. For example Figure 2a the steps of the relevant embodiments can be referred to the relevant descriptions of the following embodiments, and will not be elaborated here for the time being.

[0023] Figure 2a is a schematic flowchart of a resource information recommendation method provided for an exemplary embodiment of the present application. For example Figure 2a , the resource information recommendation method includes: 201. In response to a resource information recommendation request submitted by a target service personnel in a target service area, obtaining initial profile data and in-depth profile data of a first user, where the initial profile data is obtained by performing a user profile analysis based on the user information of the first user, and the in-depth profile data is obtained by performing a user profile analysis based on a conversation between the target service personnel and the first user; 202. Perform a potential resource demand analysis on the first user based on the initial profile data and the in-depth profile data to obtain potential multi-dimensional resource demand information of the first user; 203. Input the initial profile data, the deep profile data, the multi-dimensional resource demand information, and the multiple resource configuration information and their recommendation conditions into the AI resource information recommendation model; based on the multi-dimensional resource demand information and the recommendation conditions of the resource configuration information, select first target resource configuration information from the multiple resource configuration information and generate recommendation reason information for the first target resource configuration information; analyze the language style information of the first user based on the initial profile data and the deep profile data, and generate, based on the language style information, speech information that recommends the first target resource configuration information to the first user using the recommendation reason information; wherein the AI resource information recommendation model is obtained by fine-tuning a pre-trained model based on sample data from the target service domain; 204. Send the first target resource configuration information, recommendation reason information and speech information to the first terminal of the target service personnel, so that the target service personnel can recommend the first target resource configuration information to the first user using speech information and recommendation reason information through the communication channel between the first terminal and the second terminal of the first user.

[0024] Figure 2b A flowchart of another resource information recommendation method provided by an exemplary embodiment of the present application is shown below. Figure 2c This is a flow chart of another resource information recommendation method provided by the exemplary embodiment of this application. Figure 2b 、 Figure 2c The above technical solution is described. Figure 2c It is a schematic diagram of the modularization and hierarchicalization of various functions, specifically including the data layer, model layer and application layer. The application layer includes the rule extraction module and the fine-tuning model module. The rule extraction module is used to select various rules, and the fine-tuning model module is used to fine-tune the model. The model layer includes the reasoning part of each model, and the application layer includes a sales assistance module that assists target service personnel in recommending resource configuration information.

[0025] In this embodiment, the target service field is not specifically limited and may be, for example, a recruitment service field, a housekeeping service field, a housing service field, or a food delivery service field, etc.

[0026] In this embodiment, when the first user has a service demand, to realize the service demand, it is necessary to rely on the resource configuration information provided by the service platform to realize the corresponding service for the first user. Taking the first user as an enterprise as an example, the service can be a posting service, and the posting service can realize the recruitment needs of the enterprise. Then the corresponding resource configuration information includes post resources, and the recruitment needs of the enterprise are published through the post resources so that the enterprise can complete the recruitment. Post resources have resource types, and the resource types of post resources include but are not limited to: pictures, texts, and videos of posts. Based on this, service personnel in the corresponding field can recommend resource configuration information that is adapted to the service needs of the first user. For the convenience of description and distinction, the corresponding field can be referred to as the target service field, and the service personnel are referred to as target service personnel.

[0027] In this embodiment, target service personnel in the target service field can register an account on the recommendation platform and become members of the recommendation platform. After logging into the service platform through their account, the target service personnel can enjoy the resource information recommendation services provided by the recommendation platform. Specifically, the target service personnel can submit a resource information recommendation request for a first user on the recommendation platform to request the recommendation platform to select a first target resource configuration information that is suitable for the first user based on the resource information recommendation request, and to generate the target service personnel's recommendation reason information and speech information for recommending the first target resource configuration information to the first user. The first user is a B-end enterprise or C-end user of other applications associated with the recommendation platform. The resource information recommendation request includes the identification information of the first user, the identification information of the first terminal, and the identification information of the second terminal. The identification information of the first user can be identity information, a special code, a code name, etc. with a unique identification function. The identification information of the first terminal can be a terminal device identification, a special code, etc. with a unique identification function. The identification information of the second terminal can be a terminal device identification, a special code, etc. with a unique identification function, but is not limited to these. Resource allocation information includes: resource type and quantity, available regions, available user attributes (type, recruitment-related information), resource names that reflect the resource allocation specifications (such as the number of people available for recruitment in the example below), resource importance or priority, resource price, and so on. For example, the resource type might be the type of posting, while the resource quantity includes, but is not limited to, the number and frequency of posts that can be published.

[0028] This embodiment does not limit the specific implementation manner in which the target service personnel submit a resource information recommendation request for the first user on the recommendation platform. For example, the recommendation platform can directly provide a configuration page for the resource information recommendation request. The configuration page at least includes information configuration items for the first user, the first terminal, and the second terminal. The identification information of the first user, the first terminal, and the second terminal can be configured in these information configuration items respectively. Alternatively, the recommendation platform and / or the service platform pre-store the identification information of the first terminal used by the first user associated with the identification information of the first user, and the recommendation platform and / or the service platform pre-store the identification information of the second terminal used by the target service personnel associated with the target service personnel. In response to the resource information recommendation request submitted by the target service personnel, the recommendation platform can obtain the identification information of the first terminal and the second terminal in real time from the local or the service platform. For another example, the recommendation platform provides a user information list (users of the service platform). The user information list includes information entries for each user. Each information entry is used to display the user information of the corresponding user. The target service personnel can screen out the first user from the user information of each user displayed in the user list. The first user can be a user with potential resource configuration information recommendation requirements. When screening out the first user based on the user information of each user displayed in the user list, the possibility and degree of demand for purchasing resource configuration information can be judged according to information such as the historical order records, historical browsing records, and current browsing records of each user, so as to determine whether it is a potential user for purchasing resource configuration information. The information entry corresponding to the first user can include a request control for the resource information recommendation request. Based on this control, the resource information recommendation request can be submitted first. Alternatively, in response to the screening operation of the target service personnel on the user information list, at least one screened user is added to the candidate service list of the target service personnel. The candidate service list can carry information entries of multiple users. In response to the triggering operation of the target service personnel on the information entry corresponding to the first user in the candidate service list, a resource information recommendation request for the first user is submitted. Each information entry is bound with the identification information of the corresponding user. When submitting a resource information recommendation request for any user, the identification information of the corresponding user can be automatically carried in the resource information recommendation request, and the identification information of the target service personnel and the identification information of the first terminal device used by the target service personnel can also be automatically carried. Thus, preferentially selecting potential first users for resource configuration information recommendation can improve the conversion rate of resource configuration information.

[0029] In an embodiment of the present application, in response to the resource information recommendation request, the recommendation platform can obtain the initial portrait data and the in-depth portrait data of the first user. The initial portrait data is obtained by performing user portrait analysis based on the user information of the first user, and the in-depth portrait data is obtained by performing user portrait analysis based on the conversation content between the target service personnel and the first user.

[0030] In some embodiments, when a user of the service platform registers as a member, some basic information will be filled in; or, the user of the service platform can enjoy the right to freely post a specified number of posts. The user can use this right to post posts. Usually, the post content contains the user's basic information, demand information, or resource information that the user can provide. All of these information can be used as the user's user information for analyzing the user's initial portrait data.

[0031] Based on this, in response to a resource information recommendation request submitted by a target service personnel in a target service area, obtain the initial portrait data and in-depth portrait data of the first user, including: according to the identification information of the first user, obtain the user information of the first user, where the user information includes initial user data and initial service demand data. The initial user data contains the basic information of the first user. When the first user is a C-end user, its basic information includes, but is not limited to: age, gender, occupation, educational background, marital status, income level, appearance, geographical location, historical information, and other registration information filled in by the first user when registering an account on the service platform. The historical information includes, but is not limited to: historical browsing records, historical posting records, and historical order placement records; when the first user is a B-end enterprise, its basic information includes, but is not limited to: the business operation years, number of employees, business scope, income level, geographical location, historical resource information, and other registration information filled in by the first user when registering an account on the service platform; the initial service demand data includes, but is not limited to: the demand information filled in by the first user when registering an account on the service platform and the demand information included in the content of the post published through the free posting privilege provided by the service platform for the current demand. Taking the recruitment demand of an enterprise as an example, the enterprise information (user information) can also be the customer type, and its demand information can be, for example, the recruitment scope, recruitment positions, number of recruits, recruitment budget, recruitment cycle, prop usage preference, effect guarantee requirements, recruitment coins & prop discount cards, recruitment features, salary and benefits, etc. information; further, establish a communication channel between the first terminal and the second terminal according to the identification information of the first terminal and the identification information of the second terminal, and obtain the conversation content generated during the conversation between the target service personnel and the first user based on the communication channel. The conversation content contains the in-depth user data and in-depth service demand data of the first user. The in-depth user data refers to the more detailed basic information related to the first user mentioned by the first user during the conversation. For example, the more detailed basic information related to the business operation years of an enterprise can be the founding time of the enterprise. Another example can be the change information of the above-listed basic information or the newly generated basic information in the recent period; in addition, the more detailed basic information can also include the basic information that has not been obtained before; the in-depth service demand data refers to the more detailed service demand information of the first user that is not included in the initial service demand data mentioned during the conversation. For example, the more detailed service demand information related to the number of recruits for a certain position can be the number of female employees recruited and the number of male employees recruited. Another example can be the change information of the above-listed demand information or the newly generated demand information in the recent period; in addition, the more detailed service demand information can also include the service demand information that has not been obtained before; further, input the conversation content into a large language model to perform semantic understanding on the conversation content to obtain the in-depth user data and in-depth service demand data related to the first user;User portrait analysis is performed based on the initial user data and the initial service demand data to obtain the initial portrait data of the first user; and user portrait analysis is performed based on the in-depth user data and the in-depth service demand data to obtain the in-depth portrait data of the first user. Among them, the initial service demand information and the in-depth service demand information describe the target services required by the first user, and the execution of the target services depends on the resource configuration information. After obtaining the initial user data and the initial service demand data of the first user, in-depth user data and in-depth service demand data are obtained through a session, which can improve the richness of the data related to the first user. Based on these data, portrait analysis can be performed to improve the accuracy of the portrait data. The in-depth portrait data is more in-depth and specific than the initial portrait data, and the in-depth portrait data will contain some portrait data not included in the initial portrait data.

[0032] Among them, the large language model can be a large language model that supports multi-modal, with the ability of cross-modal and cross-language deep semantic understanding and generation. In the process of user data extraction and portrait analysis, natural language processing can be used to analyze and classify the user data to generate corresponding portrait data. The large language model can be, but is not limited to: (Large Language Models, LLMs), models of the GLM (Generalized Linear Model) series, models of the Qwen series, etc. The large language model can be obtained by training the initial large language model with sample data in the portrait field.

[0033] Optionally, according to the identification information of the first user, the user information of the first user is obtained, including: if the user information of the first user synchronized by the service platform is locally stored on the recommendation platform, then according to the identification information of the first user, the user information of the first user can be directly obtained locally, and the user information of the first user is pre-stored locally, which provides convenience for obtaining this information. Or, according to the identification information of the first user, the user information of the first user is obtained from the service platform in real time. Since the user information of the first user may be updated in real time on the service platform, in response to the resource information recommendation request submitted by the target service personnel in the target service field, obtaining the user information of the first user from the service platform in real time can obtain the latest user information and avoid missing updated user information.

[0034] Optionally, a communication channel is established between the first terminal and the second terminal based on the identification information of the first terminal and the identification information of the second terminal, and the conversation content generated during the conversation between the target service personnel and the first user through the communication channel is obtained, including: in response to a call request for the second user sent by the target service personnel based on the outbound call control provided by the recommendation platform, the recommendation platform makes an outbound call to the second terminal to establish a communication channel between the first terminal and the second terminal. The recommendation platform can serve as a transfer station for the communication channel between the first terminal and the second terminal. In other words, the recommendation platform is the transfer station for this communication channel, and the recommendation platform can obtain in real time the conversation content of the first terminal and the second terminal during the conversation through this communication channel. Or, after the recommendation platform sends the resource configuration information, recommendation reason information, and script information matched for the first user to the first terminal, within a preset time, the recommendation platform will automatically initiate a dual call to the first terminal and the second terminal to establish a communication channel between the first terminal and the second terminal. The recommendation platform can serve as a transfer station for the communication channel between the first terminal and the second terminal. In other words, the recommendation platform is the transfer station for this communication channel, and the recommendation platform can obtain in real time the conversation content of the first terminal and the second terminal during the conversation through this communication channel. Through the above method, the recommendation platform can obtain in real time the conversation content between the target service personnel and the first user, which is beneficial to updating the user information of the first user in a timely manner based on the conversation content on the basis of the already obtained user information and improving the richness of the user information.

[0035] Optionally, the conversation content is input into a large language model for semantic understanding of the conversation content to obtain in-depth user data and in-depth service demand data related to the first user, including: inputting the conversation content into the large language model for semantic understanding of the conversation content to obtain the semantic information of the conversation content; classifying the semantic information of the conversation content from the user data dimension and the demand data dimension to obtain the semantic information of the user data dimension and the semantic information of the demand data dimension; respectively performing semantic conversion on the semantic information of the user data dimension and the semantic information of the demand data dimension to obtain in-depth user data and in-depth service demand data related to the first user. By respectively extracting the in-depth user data and the in-depth service demand data through semantic understanding, the efficiency and accuracy of data extraction can be improved, thereby improving the generation efficiency of resource information.

[0036] It should be noted that during the process of obtaining the conversation content, the large language model can be directly used to perform semantic understanding on the conversation content to obtain in-depth user data and in-depth service demand data related to the first user. Compared with performing semantic understanding on the conversation content after obtaining the conversation content, the data analysis efficiency is improved, and thus the generation efficiency of resource information can be improved.

[0037] It should also be noted that the number of communications through the established communication channel can be multiple, and the session content can be the sum of the session contents after multiple session communications. During the process of retrieving the session content each time, semantic understanding can be performed to obtain the in-depth user data and in-depth service demand data related to the first user for that session. Further, resource information can be generated based on the data each time, and the corresponding resource configuration information can be recommended to the user until the user is satisfied. Alternatively, after the in-depth user data and in-depth service demand data related to the first user obtained from multiple sessions meet the requirements of the target service personnel, the data for each time can be integrated, and resource information can be generated based on the integrated data.

[0038] Optionally, user portrait analysis is performed based on the initial user data and initial service demand data to obtain the initial portrait data of the first user, including: inputting the initial user data and initial service demand data into the target portrait analysis model, performing semantic understanding on the initial user data and initial service demand data from the portrait dimension to obtain the target portrait semantic information set; performing semantic classification on the portrait semantic information in the target portrait semantic information set to obtain multiple target portrait semantic categories; based on the mapping relationship between the portrait semantic categories and portrait information pre-learned in the target domain, mapping the portrait information for multiple target portrait semantic categories to obtain the initial portrait data of the first user. By classifying the semantic information of the user's initial data into portrait semantic categories and based on the mapping relationship between the portrait semantic categories and portrait information, obtaining the initial portrait data of the first user can improve the accuracy of the initial portrait data and the analysis efficiency of the initial portrait data.

[0039] Optionally, user portrait analysis is performed based on the in-depth user data and in-depth service demand data to obtain the in-depth portrait data of the first user, including: inputting the in-depth user data and in-depth service demand data into the target portrait analysis model, performing semantic understanding on the in-depth user data and in-depth service demand data from the portrait dimension to obtain the target portrait semantic information set; performing semantic classification on the portrait semantic information in the target portrait semantic information set to obtain multiple target portrait semantic categories; based on the mapping relationship between the portrait semantic categories and portrait information pre-learned in the target domain, mapping the portrait information for multiple target portrait semantic categories to obtain the in-depth portrait data of the first user. By classifying the semantic information of the user's in-depth data into portrait semantic categories and based on the mapping relationship between the portrait semantic categories and portrait information, obtaining the in-depth portrait data of the first user can improve the accuracy of the in-depth portrait data and the analysis efficiency of the in-depth portrait data.

[0040] In the embodiments of the present application, after obtaining the initial portrait data and the depth portrait data of the first user, potential resource demand analysis can be performed on the first user based on the initial portrait data and the depth portrait data to obtain the potential multi-dimensional resource demand information of the first user. The multi-dimensional resource demand information can be understood as multi-dimensional business opportunity information. From the perspective of the resource provider, the multi-dimensional resource demand information reflects the business opportunity information existing for the resource provider by the user from multiple dimensions. By combining the initial portrait data and the depth portrait data of the first user and analyzing the potential resource demand information of the first user, the accuracy of the resource demand information can be improved. In addition, by performing a refined analysis of the potential resource demand information of the first user from multiple dimensions, the resource demand information for each dimension can be accurately obtained, which is beneficial to subsequently matching more suitable resource configuration information for the first user based on the accurate multi-dimensional resource demand information and improving the conversion rate of the resource configuration information. Among them, the multi-dimensional resource demand information is detailed information about the potential business needs and cooperation possibilities of the first user mined from different angles and levels. The multi-dimensional resource demand information includes, but is not limited to: the level of the budget, the required duration of the resource configuration information, the usage frequency of the resource configuration information, service function requirements, brand loyalty, and cooperation willingness. By performing a refined analysis of these multi-dimensional resource demand information, more accurate and more suitable resource configuration information can be provided for the user, thereby improving the conversion rate of the resource configuration information and user satisfaction.

[0041] In some embodiments, potential resource demand analysis is performed on the first user based on the initial portrait data and the depth portrait data to obtain the potential multi-dimensional resource demand information of the first user, including: inputting the initial portrait data and the depth portrait data into the target resource demand analysis model, performing semantic understanding on the initial portrait data and the depth portrait data from the resource demand dimension to obtain the target resource demand semantic information set, and the target resource demand semantic information set includes the resource demand semantic information contained in the initial portrait data and the depth portrait data respectively and jointly; performing semantic classification on the resource demand semantic information in the target resource demand semantic information set to obtain multiple target semantic categories; based on the mapping relationship between the semantic categories and the resource demand information in the pre-learned target service field, performing mapping of the resource demand information on the multiple target semantic categories to obtain the potential multi-dimensional resource demand information of the first user. By jointly analyzing the potential resources demanded by the first user in combination with the initial portrait data and the depth portrait data, the accuracy of the multi-dimensional resource demand information can be improved, which is beneficial to improving the matching degree between the recommended resource configuration information and the first user.

[0042] Further optionally, such as Figure 2eAs shown, the above-mentioned target resource requirement analysis model can be trained as follows: Obtain a sample data set in the target service domain, where the sample data set includes multiple sample portrait data, the sample resource requirement semantic information corresponding to each sample portrait data, and the sample semantic category corresponding to each sample resource requirement semantic information; Input the multiple sample portrait data into the initial resource requirement analysis model, perform semantic understanding on the multiple sample portrait data from the resource requirement dimension, and obtain the intermediate resource requirement semantic information; Perform semantic classification on the intermediate resource requirement semantic information to obtain multiple intermediate semantic categories, and learn the mapping relationship between the intermediate semantic categories and the intermediate resource requirement semantic information; Based on the mapping relationship, map the multiple intermediate semantic categories to obtain the intermediate resource requirement information; Calculate the model loss function based on the intermediate resource requirement semantic information and the sample resource requirement semantic information, as well as the intermediate semantic category and the sample semantic category. When the model loss function does not meet the model training termination condition, continue to train the initial resource requirement analysis model until the model loss function meets the model training termination condition, and obtain the target resource requirement analysis model. After obtaining the target resource requirement analysis model, the model performance will also be evaluated. After passing the evaluation, the model will be deployed to the corresponding operating environment. And during the use of this model, it can also be optimized in real time according to the usage data to improve the performance of this model. Among them, the initial resource requirement analysis model is selected from the models to be pre-trained according to the target service domain and trained according to the training samples in the pre-training data preparation library, and the model is fine-tuned through the sample data in the target service domain. It can improve the accuracy of the target resource requirement model in analyzing the resource requirements in the target service domain, thereby improving the accuracy of the potential multi-dimensional resource requirement information of the first user.

[0043] Optionally, calculating the model loss function based on the intermediate resource requirement semantic information and the sample resource requirement semantic information, as well as the intermediate semantic category and the sample semantic category, includes: calculating the first loss function between the intermediate resource requirement semantic information and the sample resource requirement semantic information, and calculating the second loss function between the intermediate semantic category and the sample semantic category, both of which are used as the model loss function; or, calculating the first loss function between the intermediate resource requirement semantic information and the sample resource requirement semantic information, and calculating the second loss function between the intermediate semantic category and the sample semantic category, and performing a weighted sum of the first loss function and the second loss function to obtain the model loss function. By using multiple loss functions alone or in combination, the model can be fine-tuned to improve the accuracy of the model.

[0044] In this embodiment, each resource configuration information has its own applicable conditions, which include but are not limited to: the user attributes applicable to this resource configuration information and the attribute information of the target service. The attribute information of the target service includes multiple attributes of the target service and different attribute values for each attribute. Among them, user attributes are attributes used to describe user characteristics, such as user ID, user type, user level, etc. The multiple attributes of the target service are attributes used to describe service characteristics, such as service type, service level, service availability, etc. The attribute value refers to a specific value corresponding to each attribute, which is used to specifically describe a certain characteristic of a user or a service. More specifically, the applicable conditions of each resource configuration information specifically refer to a series of regulations that any user needs to meet when using this resource configuration information. The applicable conditions of these resource configuration information include which users can enjoy the various rights and / or preferences provided by this resource configuration information. At the same time, the applicable conditions of the resource configuration information also clarify the content in aspects such as the expiration date, usage scope, and usage restrictions of the resource configuration information, so as to ensure that users can fully understand and abide by the relevant regulations during the usage process, thereby protecting the rights and interests of both parties.

[0045] Based on the applicable conditions of each resource configuration information described above, in order to improve the adaptability of the resource configuration information selected for the first user to this first user, the multi-dimensional resource requirement information and multiple resource configuration information and their recommended conditions can be input into the AI resource information recommendation model. Based on the multi-dimensional resource requirement information and the recommended conditions of the resource configuration information, the first target resource configuration information is selected from multiple resource configuration information and the recommended reason for the first target resource configuration information is generated. Among them, the recommended conditions of the resource configuration information specifically refer to those used to accurately recommend the most suitable resource configuration information for users according to the multi-dimensional resource requirement information of the first user. These resource configuration information rules aim to maximize user satisfaction while improving the conversion rate of the resource configuration information and the user retention rate.

[0046] In some embodiments, the initial portrait data, the depth portrait data, the multi-dimensional resource requirement information, the multiple resource configuration information, and their recommendation conditions are input into the AI resource information recommendation model. Based on the recommendation conditions of the multi-dimensional resource requirement information and the resource configuration information, the target resource configuration information is selected from the multiple resource configuration information, including: inputting the initial portrait data, the depth portrait data, the multi-dimensional resource requirement information, the multiple resource configuration information and their recommendation conditions, and the applicable conditions of the multiple resource configuration information into the AI resource information recommendation model, and performing semantic matching between the multi-dimensional resource requirement information and the applicable conditions of each resource configuration information to determine the target applicable conditions that are semantically matched with the multi-dimensional resource requirement information; taking the resource configuration information with the target applicable conditions among the multiple resource configuration information as the candidate resource configuration information; and selecting the first target resource configuration information from the candidate resource configuration information based on the resource configuration information recommendation conditions and the multi-dimensional resource requirement information. Performing semantic matching between the resource requirement information of each dimension and the applicable conditions of each resource configuration information respectively improves the accuracy of semantic matching, thereby improving the matching degree between the first target resource configuration information and the first user.

[0047] It should be noted that the applicable conditions of each resource configuration information and the recommendation conditions of the resource configuration information are different rules, and their contents and functions are different from each other.

[0048] In order to provide users with multi-faceted choices to meet the needs of different users, and at the same time to further improve the matching degree between the first target service and the first user, in this embodiment, the recommendation conditions of the resource configuration information can be multiple. Based on the recommendation conditions of the resource configuration information and the multi-dimensional resource requirement information, selecting the first target resource configuration information from the candidate resource configuration information includes: grouping the multiple resource configuration information based on the recommendation conditions of each resource configuration information to obtain an initial resource configuration information set adapted to the recommendation conditions of each resource configuration information; for each initial resource configuration information set, analyzing the local matching degree between each resource configuration information in the initial resource configuration information set and the resource requirement information of each dimension in the multi-dimensional resource requirement information from the service content dimension, calculating the overall matching degree according to the local matching degree between each resource configuration information and the resource requirement information of each dimension in the multi-dimensional resource requirement information, and taking the resource configuration information with the overall matching degree greater than the corresponding threshold as the first target resource configuration information under the recommendation conditions of this resource configuration information.

[0049] The following is an example of resource configuration information: "Resource Configuration Information Number - Nationwide Recruitment - Version Model - Standard Edition Quarterly Member Resource Configuration Information (Resource Configuration Information Name) Customer Analysis: 1. Customer Type: Direct Recruitment Customer 2. Recruitment scope: Nationwide 3. Recruitment positions: (1,4); 4. Number of recruits: (2,6); 5. Recruitment budget (1000-2000); 6. Recruitment cycle: short-term recruitment, seasonal recruitment; 7. Preferences for prop usage: exposure, efficiency; 8. Effect guarantee requirements: None; 9. Recruitment Coins & Item Discount Cards: None 10. Recruitment characteristics: early adopters, with extremely low budgets and concerns about the platform’s effectiveness.

[0050] Resource allocation information selling points: Quarterly resource allocation information can be posted up to 3 times, and super pinning can increase exposure. Combined with talent radar and high-speed calling cards, it can efficiently screen and contact job seekers.

[0051] Notes: 1. Direct recruitment customers who are unable to sign up for the monthly personal value-added resource allocation information (local) may consider purchasing the quarterly membership resource allocation information (national).

[0052] 2. The posting limit for the eight categories of popular positions is five or fewer: food delivery riders, delivery / delivery personnel, online car-hailing drivers, commercial drivers, designated drivers, taxi drivers, shuttle bus drivers, and passenger transport drivers.

[0053] 3. Super pinning within the quarterly member resource allocation information (national) cannot be used for the above eight categories.

[0054] In some embodiments, the multi-dimensional resource demand information includes: attribute information of the first user, level information of budget demand, and service demand information, the service demand information includes: basic service demand, core service demand, and service demand duration; the recommendation conditions of the resource configuration information include optimal resource configuration information recommendation conditions, medium resource configuration information recommendation conditions, and minimum resource configuration information recommendation conditions. The optimal resource configuration information recommendation conditions are used to determine resource configuration information with a high budget level and that meets the service demand information, the medium resource configuration information recommendation conditions are used to determine resource configuration information with a low budget level, that meets the core service demand and its service demand duration, and the minimum resource configuration information recommendation conditions are used to determine resource configuration information that meets the basic service demand and its service demand duration. For example, different first target resource configuration information templates recommended for the first user are roughly as follows: Optimal resource allocation information: high value, high matching (sufficient budget / demand fit); Medium resource allocation information: high cost-effectiveness, covering core needs (limited budget); Guaranteed resource allocation information: covering basic services, low threshold (new customers / short-term cooperation).

[0055] Based on the relevant content of the above multi-dimensional resource requirement information, in order to further improve the adaptability of the first target service to the first user, for each initial resource allocation information set, analyze the local adaptability of each resource allocation information in the initial resource allocation information set to the resource requirement information of each dimension in the multi-dimensional resource requirement information from the service content dimension, calculate the overall adaptability according to the local adaptability of each resource allocation information to the resource requirement information of each dimension in the multi-dimensional resource requirement information, and use the resource allocation information with the overall adaptability greater than the corresponding threshold as the first target resource allocation information under the recommended conditions of this resource allocation information, including: for the initial resource allocation information set under the recommended conditions of the optimal resource allocation information, respectively analyze the multiple first local adaptabilities of each resource allocation information in the initial resource allocation information set in the dimensions of budget requirement level, basic service requirement, core service requirement, and service requirement duration; based on the multiple first local adaptabilities, calculate the first overall adaptability; use the resource allocation information corresponding to the first overall adaptability greater than the first threshold as the first target resource allocation information under the recommended conditions of the optimal resource allocation information; for the initial resource allocation information set under the recommended conditions of the medium resource allocation information, respectively analyze the multiple second local adaptabilities of each resource allocation information in the initial resource allocation information set in the dimensions of budget requirement level, core service requirement, and service requirement duration; based on the multiple second local adaptabilities, calculate the second overall adaptability; use the resource allocation information corresponding to the second overall adaptability greater than the second threshold as the first target resource allocation information under the recommended conditions of the medium resource allocation information; for the initial resource allocation information set under the recommended conditions of the guaranteed resource allocation information, respectively analyze the multiple third local adaptabilities of each resource allocation information in the initial resource allocation information set in the dimensions of budget requirement level, basic service requirement, and service requirement duration; based on the multiple third local adaptabilities, calculate the third overall adaptability; use the resource allocation information corresponding to the third overall adaptability greater than the third threshold as the first target resource allocation information under the recommended conditions of the guaranteed resource allocation information.

[0056] Taking the first user as an enterprise and the target service field as the recruitment service field as an example, the information of this enterprise is as follows: "* Company name: A certain car rental company at a certain location; * Establishment time: ** year ** month; * Employee scale: 10 - 50 people; * Main business: New energy vehicle rental; * Recruitment positions: Rental consultants, vehicle dispatchers, etc.; Recruitment pain points: * Low resume matching rate: Recruitment through traditional classified information platforms has a resume matching rate of less than 20%; * Core issues: Insufficient industry awareness and lack of local resources. ”

[0057] Based on the above enterprise information, the optimal resource allocation information, medium resource allocation information, and minimum resource allocation information are determined as follows: “Optimal resource allocation information: Recommended: Yes. Target City: First-tier cities. Business Type: New / Renewal. Resource Allocation Information Number: PKG_8180. Recommended Resource Allocation Information Name: Resource Allocation Information Number - Quanwangzhao 3.0 Standard Edition Annual Member Resource Allocation Information.

[0058] Customer Analysis: 1. Customer type: First-tier direct recruitment customers; 2. Recruitment scope: nationwide; 3. Recruitment positions: (3, 8); 4. Number of recruits; (10, 25); 5. Recruitment budget (more than 8,000); 6. Recruitment cycle: Continuous recruitment throughout the year; 7. Prop usage preference: flexible; 8. Effect guarantee requirements: None; 9. Recruitment Coins & Item Discount Cards: 5500 Recruitment Coins, 8 35% discount cards; 10. Recruitment Characteristics: Medium budget with long-term recruitment needs. Resource Allocation Information Selling Points: 8 positions available, 5,500 Recruitment Coins are equivalent to cash on the platform, a better value than 6,180, and 8 discount cards are available for purchase at a 35% discount. Note: Postings are limited to 5 of the 8 popular job categories: Food Delivery Rider, Delivery / Courier, Ride-Hailing Driver, Commercial Driver, Designated Driver, Taxi Driver, Shuttle Bus Driver, and Passenger Driver.

[0059] Medium resource configuration information: Is it a primary promotion: Yes. City Tier: Nationwide. Business Type: New Sign-Up / Land Promotion. Resource Allocation Information Number: PKG_4980. Recommended Resource Allocation Information Name: Resource Allocation Information Number - Quanwangzhao 3.0 Standard Edition Full-Year Member Resource Allocation Information.

[0060] Customer Analysis: 1. Customer type: Direct recruitment customers; 2. Recruitment scope: nationwide; 3. Recruitment positions: (3, 8); 4. Number of recruits (6, 20); 5. Recruitment budget (3000-5000); 6. Recruitment cycle: Continuous recruitment throughout the year; 7. Prop usage preference: flexible; 8. Effect guarantee requirements: None; 9. Recruitment Coins & Item Discount Cards: 3600 Recruitment Coins, 8 35% off discount cards; 10. Recruitment Features: Low budget, long-term recruitment needs. Resource Allocation Information Selling Points: Includes 8 positions listed, 3,600 Recruitment Coins (useable as cash on the platform), 8 discount cards with a 35% discount, and other features for higher visibility. Note: Postings are limited to 5 of the 8 popular job categories: Food Delivery Rider, Delivery / Courier, Ride-Hailing Driver, Commercial Driver, Designated Driver, Taxi Driver, Shuttle Bus Driver, and Passenger Driver.

[0061] Minimum resource allocation information: Is it a primary promotion: Yes. City Tier: Nationwide. Business Type: New Sign-Up / Land Promotion. Resource Allocation Information Number: PKG_3980. Recommended Resource Allocation Information Name: Resource Allocation Information Number - Quanwangzhao 3.0 Standard Edition Full-Year Member Resource Allocation Information.

[0062] Customer Analysis: 1. Customer type: Direct recruitment customers; 2. Recruitment scope: nationwide; 3. Recruitment positions: (3, 8); 4. Number of recruits; (5, 15); 5. Recruitment budget (3000-5000); 6. Recruitment cycle: Continuous recruitment throughout the year; 7. Prop usage preference: flexible; 8. Effect guarantee requirements: None; 9. Recruitment Coins & Item Discount Cards: 2400 Recruitment Coins, 8 32% off discount cards; 10. Recruitment Features: Low budget, long-term recruitment needs. Resource Allocation Information Selling Point: The lowest-priced nationwide resource allocation information, including 8 positions, 2,400 Recruitment Coins, and 8 32% off item discount cards, which can be combined for greater flexibility. Note: Postings are limited to 5 of the 8 popular job categories: Food Delivery Rider, Delivery / Courier, Ride-hailing Driver, Commercial Driver, Designated Driver, Taxi Driver, Shuttle Bus Driver, and Passenger Driver.

[0063] Furthermore, the AI resource information recommendation model can also generate recommendation reason information for the first target resource configuration information, so that the target service personnel can recommend the first target resource configuration information to the first user based on the recommendation reason information. The recommendation reason information refers to the commentary of the target service personnel recommending the first target resource configuration information to the first user.

[0064] In an optional embodiment, the recommended reason information for generating the first target resource configuration information includes: generating recommended reason information of the service demand type based on the service demand pointed to by the multi-dimensional resource demand information and the configured service represented by the configuration content of the first target resource configuration information; generating recommended reason information of the budget type based on the budget demand pointed to by the multi-dimensional resource demand information and the configured price represented by the configuration content of the first target resource configuration information; integrating the recommended reason information of the service demand type and the recommended reason information of the budget type to generate recommended reason information for recommending the first target resource configuration information to the first user. The recommended reason information can ensure the matching of resource configuration and user needs, enhance persuasion, improve the conversion rate of resource configuration information, and enhance the user experience.

[0065] Furthermore, in order to improve the conversion rate of the resource configuration information recommended by the target service personnel to the first user, the AI resource information recommendation model can also analyze the language style information of the first user based on the initial portrait data and the in-depth portrait data, and generate the conversation information for recommending the first target resource configuration information to the first user with the recommended reason information based on the language style information, so that the target service personnel can use the conversation skills provided by the conversation information to recommend the first target resource configuration information to the first user with the recommended reason information. Among them, the language style information refers to a series of characteristics and attributes reflected in text, spoken language or other forms of language communication, which can reflect the personality, emotion, intention, context and cultural background of the speaker or writer. This information can help the target service personnel better understand the language habits of the first user, so as to improve the acceptance degree of the first user for the recommendation process. The conversation information refers to the conversation skills for recommending the first target resource configuration information to the first user. The conversation information corresponds to a conversation template library, and the appropriate conversation template can be selected from the template library according to specific requirements (such as user type) to generate the conversation information based on the conversation model. The conversation template is used to standardize the content and structure of the conversation information.

[0066] In an optional embodiment, analyzing the language style information of the first user based on the initial portrait data and the in-depth portrait data includes: inputting the initial portrait data and the in-depth portrait data into a pre-trained language style analysis model, and extracting the features related to the language style from the initial portrait data and the in-depth portrait data. The features include but are not limited to word usage frequency, sentence structure, emotional tendency, semantic density, etc.; based on the extracted features related to the language style, analyzing the language style information of the first user. The language style information includes but is not limited to formal and informal styles, spoken and written styles, emotional expression intensity, etc.

[0067] In an optional embodiment, speech information for recommending the first target resource configuration information to the first user with recommendation reason information is generated based on the language style information of the first user, including: generating speech information based on the language style information and the recommendation reason information for recommending the first target resource configuration information to the first user. In this way, user needs can be met more accurately, and user satisfaction and the conversion rate of resource configuration information can be improved. More specifically, speech information can be generated based on the language style information of the first user and the recommendation form corresponding to the recommendation reason information, so that the speech information is adapted not only to the language style of the first user, but also to the recommendation form of the recommendation reason information, thereby improving the first user's acceptance of the first target resource configuration information. Among them, the recommendation form refers to the presentation method and structure of the recommendation content contained in the recommendation reason information, which determines how the recommendation reason information is organized and presented to the user. The recommendation form can be adjusted according to different user needs, scenarios and language styles to improve the user's acceptance and satisfaction.

[0068] Furthermore, to enhance the first user's trust in the resource configuration information recommendation service, historical user cases that have previously purchased resource configuration information and have given favorable evaluations of the resource configuration information they purchased can be selected and provided to the first user for reference. Specifically, a second user can be identified from the historical users, whose multi-dimensional resource demand information matches the first user's multi-dimensional resource demand information to a greater degree than a fourth threshold, and whose evaluation of the second target resource configuration information recommended and purchased by the target service personnel to the second user is greater than a fifth threshold. This step can be considered as calculating the similarity between the multi-dimensional resource demand information of the first and second users.

[0069] In some optional embodiments, determining a second user from historical users includes: obtaining historical evaluation information, the historical evaluation information including multi-dimensional resource demand information of multiple historical users, the purchased second target resource configuration information and configuration content, and the evaluation information of each historical user on the purchased second target resource configuration information and the corresponding evaluation level; based on the multi-dimensional resource demand information of multiple historical users, determining a target historical user from multiple historical users whose matching degree with the multi-dimensional resource demand information of the first user is greater than a fourth threshold; determining a second user from the target historical users whose evaluation level of the purchased second target resource configuration information is higher than a fifth threshold; and pushing the historical evaluation information of the second user to the second terminal so that the first user can understand the historical evaluation information of the second target resource configuration information recommended by the target service personnel to the second user.

[0070] Accordingly, recommendation reason information for the first target resource configuration information is generated, including: generating service demand type recommendation reason information based on the service demand pointed to by the multi-dimensional resource demand information and the resource configuration information service represented by the configuration content of the first target resource configuration information; generating budget type recommendation reason information based on the budget demand pointed to by the multi-dimensional resource demand information and the resource configuration information price represented by the configuration content of the first target resource configuration information; generating historical evaluation type recommendation reason information based on the multi-dimensional demand information of the second user, the purchased second target resource configuration information, and the historical evaluation information pointed to by the evaluation level of the purchased second target service; integrating the service demand type recommendation reason information, the budget type recommendation reason information, and the historical evaluation type recommendation reason information to generate recommendation reason information for recommending the first target resource configuration information to the first user; and analyzing the language style information of the first user based on the initial portrait data and the deep portrait data, and generating speech information based on the language style information to recommend the first target resource configuration information to the first user with the recommendation reason information.

[0071] Further, if Figure 2e As shown, after obtaining the first target resource configuration information, recommendation reason information and speech information, resource information can be generated based on a preset resource information structure, and the structured resource information can be sent to the target service personnel.

[0072] Taking the recruitment of the above car rental company as an example, the reasons for service requirements are as follows: Your company is currently in a stage of rapid development, recruiting positions such as rental consultants and vehicle dispatchers, and there are core problems such as low resume matching, insufficient industry awareness, and lack of local resources. In response to these pain points, the resource allocation information we recommend for you provides recruitment services nationwide, which can help you expand the recruitment scope and attract more professional talents. Among them, the standard annual membership resource allocation information (optimal resource allocation information) supports continuous recruitment throughout the year, can meet your medium- and long-term recruitment needs, and provides 8 positions to be listed, which can cover your current recruitment position requirements. The reasons for the budget are as follows: According to your recruitment budget, we provide you with resource allocation information options at different price levels: Standard annual membership resource allocation information (optimal resource allocation information): Suitable for enterprises with medium budgets and long-term recruitment needs. The price of the resource allocation information is 8,180 yuan, providing 5,500 recruitment coins, which are equivalent to cash use, with high cost performance, and comes with 8 65% discount cards, which can be used to purchase value-added services such as top placement to further improve the recruitment effect. Standard annual membership resource allocation information (medium resource allocation information): Suitable for enterprises with budgets between 3,000 and 5,000 yuan. The price of the resource allocation information is 4,980 yuan, providing 3,600 recruitment coins, which are also equivalent to cash use, and comes with 8 65% discount cards, which can meet your recruitment needs and achieve a higher exposure rate at the same time. Standard annual membership resource allocation information (guaranteed resource allocation information): Suitable for enterprises with lower budgets. The price of the resource allocation information is 3,980 yuan, providing 2,400 recruitment coins, and comes with 8 68% prop discount cards. It is the national resource allocation information with the lowest price, with more flexible combined use, and can help you achieve your recruitment goals within a limited budget. The reasons for historical evaluations are as follows: We refer to the multi-dimensional requirement information, purchased resource allocation information, and evaluation levels of resources of enterprises of similar scale and industry (such as the second user). These enterprises are generally satisfied with the recruitment effect of the resource allocation information and believe that the resource allocation information can effectively improve the resume matching degree and recruitment efficiency. For example, the enterprise that purchased the medium resource allocation information feedback that this resource allocation information helped them save time and costs during the recruitment process and attracted more high-quality candidates at the same time. Therefore, we believe that these resource allocation information can also meet your recruitment needs and help you solve the current recruitment pain points.

[0073] Correspondingly, the wording information is as follows: The company is a car rental company, and it pays more attention to the service capabilities and affinity of the drivers. When communicating with users, it should pay attention to the following aspects: Affinity: The language style is friendly and kind, which brings it closer to customers; Cultural adaptability: The language style is in line with business communication habits, while taking into account the industry characteristics and cultural background of the company; Guidance: By gradually introducing the characteristics and advantages of resource allocation information, guide customers to pay attention to recommended resource allocation information; Targetedness: Closely combine the customer's background, pain points and needs to provide personalized resource allocation information recommendations; Flexibility: Provide multiple resource allocation information options to meet different budget needs; Professionalism: Use professional recruitment service terminology to reflect professionalism.

[0074] Based on the above recommendation reason information and speech information, the target service personnel recommends the resource configuration information to the user as follows: Dear car rental company manager: Hello! I'm a member of the recruitment platform Name. I'm honored to be connected with your company. We understand that your company is rapidly expanding in the new energy vehicle rental sector and is currently facing some recruitment challenges, particularly regarding resume matching and local resources. We understand that recruitment is crucial to business growth, and we hope to provide you with some practical solutions.

[0075] Before contacting you, we conducted an in-depth analysis of your company's business scope, recruitment needs, and budget. Based on this information, we have carefully selected three recruitment resource allocations for you, hoping to meet your different needs.

[0076] First, we recommend the optimal resource allocation. This resource allocation is ideal for companies like yours with medium- to long-term recruitment needs. It supports year-round recruitment and offers eight positions, meeting your current job requirements. The resource allocation costs 8,180 yuan, including 5,500 Recruitment Coins, which is equivalent to cash and offers excellent value for money. In addition, we've included eight 35% discount cards, which you can use to purchase value-added services like top-ranking to further enhance your recruitment results.

[0077] If you have stricter budget constraints, we offer two resource allocation options. The medium resource allocation costs 4,980 yuan and offers 3,600 Recruitment Coins, which are equivalent to cash. It also comes with eight 35% discount cards, meeting your recruitment needs while achieving higher exposure. The guaranteed resource allocation is the lowest-priced national resource allocation, priced at 3,980 yuan, offering 2,400 Recruitment Coins and eight 32% discount cards. This combination offers greater flexibility and can help you achieve your recruitment goals within a limited budget.

[0078] We also reviewed the evaluations of these resourcing information from companies of similar size and industry. Companies that purchased mid-level resourcing information reported that it helped them save time and costs during the recruitment process while attracting more high-quality candidates. Therefore, we believe these resourcing information can also meet your recruitment needs and help you address your current recruitment pain points.

[0079] During our conversations with you, we noted your company's emphasis on effective recruitment and sound budget planning. We are confident that our professional services and carefully designed resource allocation information will ensure satisfactory recruitment results for your company. If you have any questions about the resource allocation information or require further information on other resource allocation details, please feel free to contact me. We look forward to working with you and supporting your business growth!

[0080] In the technical solutions provided by the above-mentioned embodiments of the present application, an AI resource information recommendation model is utilized to determine the first target resource configuration information from a variety of resource configuration information based on the recommendation conditions of the first user's potential multi-dimensional resource demand information and resource configuration information, and quickly and accurately match the adapted resource configuration information for the user; in addition, the language style information of the first user can be analyzed based on the initial and deep portrait data of the first user, and recommendation reason information and speech information for recommending the first target resource configuration information to the first user are generated accordingly. The target service personnel can use the speech skills provided by the speech information to recommend the first target resource configuration information to the first user with the recommendation reason information, thereby improving the persuasiveness of the recommended resource configuration information, and also adapting the language style to the first user, thereby improving the user's acceptance of the recommendation process and improving the conversion rate of the resource configuration information.

[0081] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 3 As shown, it includes: a memory 30a and a processor 30b; the memory 30a is used to store computer programs; the processor 30b is coupled with the memory 30a and is used to execute the computer programs to perform the steps in the above method embodiment.

[0082] Furthermore, if Figure 3 As shown, the server also includes: a communication component 30c, a display 30d, a power component 30e, an audio component 30f and other components. Figure 3 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 3 Components shown.

[0083] The detailed implementation and beneficial effects of the electronic device provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated on here.

[0084] An exemplary embodiment of the present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the steps in the above method embodiments.

[0085] An exemplary embodiment of the present application also provides a computer program product, which includes computer programs / instructions that, when executed by a processor, enable the processor to implement the steps in the above method embodiments.

[0086] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0087] The above-mentioned communication component is configured to facilitate communication between the device where the communication component is located and other devices in a wired or wireless manner. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

[0088] The above-mentioned display includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from users. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operations.

[0089] The above-mentioned power supply component provides power for various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.

[0090] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), which is configured to receive external audio signals when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory or sent via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals.

[0091] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk memories, Compact Disc Read-Only Memories (CD-ROMs), optical memories, etc.) containing computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0093] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the function specified in one or more processes and / or blocks Figure 1 in one or more processes and / or blocks Figure 1 specified in the flowchart.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more processes and / or blocks Figure 1 in one or more processes and / or blocks Figure 1 specified in the flowchart.

[0095] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), an input / output interface, a network interface, and memory.

[0096] The memory may include non-permanent memory in the form of computer-readable media, random access memory (Random Access Memory, RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0097] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0099] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A resource information recommendation method, characterized in that, include: In response to a resource information recommendation request submitted by a target service personnel in a target service area, obtaining initial profile data and in-depth profile data of a first user, wherein the initial profile data is obtained by performing a user profile analysis based on the user information of the first user, and the in-depth profile data is obtained by performing a user profile analysis based on the conversation content between the target service personnel and the first user; Performing a potential resource demand analysis on the first user based on the initial portrait data and the in-depth portrait data to obtain potential multi-dimensional resource demand information of the first user; Inputting the initial portrait data, the depth portrait data, the multi-dimensional resource demand information, and the multiple resource configuration information and their recommendation conditions into an AI resource information recommendation model; based on the multi-dimensional resource demand information and the recommendation conditions of the resource configuration information, selecting first target resource configuration information from the multiple resource configuration information and generating recommendation reason information for the first target resource configuration information; Analyze the language style information of the first user based on the initial profile data and the deep profile data, and generate, based on the language style information, speech information recommending the first target resource configuration information to the first user using the recommendation reason information; wherein the AI resource information recommendation model is obtained by fine-tuning a pre-trained model based on sample data of the target service field; The first target resource configuration information, the recommendation reason information and the speech information are sent to the first terminal of the target service personnel, so that the target service personnel can use the speech information and the recommendation reason information to recommend the first target resource configuration information to the first user through the communication channel between the first terminal and the second terminal of the first user.

2. The method according to claim 1, wherein The resource information recommendation request includes identification information of the first user, identification information of the first terminal, and identification information of the second terminal; In response to a resource information recommendation request submitted by a target service personnel in a target service area, obtaining initial profile data and in-depth profile data of a first user, including: Acquire user information of the first user according to the identification information of the first user, the user information including initial user data and initial service demand data; establishing a communication channel between the first terminal and the second terminal according to the identification information of the first terminal and the identification information of the second terminal, and obtaining conversation content generated during the conversation between the target service personnel and the first user based on the communication channel; Inputting the conversation content into a large language model and performing semantic understanding on the conversation content to obtain deep user data and deep service demand data related to the first user; Performing user portrait analysis based on the initial user data and the initial service demand data to obtain initial portrait data of the first user; and Perform user portrait analysis based on the in-depth user data and the in-depth service demand data to obtain in-depth portrait data of the first user.

3. The method according to claim 1, characterized in that, Based on the initial portrait data and the depth portrait data, perform a potential resource demand analysis for the first user to obtain the first user's potential multi-dimensional resource demand information, including: Input the initial portrait data and the depth portrait data into a target resource demand analysis model, and perform semantic understanding on the initial portrait data and the depth portrait data from the resource demand dimension to obtain a target resource demand semantic information set, where the target resource demand semantic information set includes the resource demand semantic information contained in the initial portrait data and the depth portrait data respectively and jointly; Perform semantic classification on the resource demand semantic information in the target resource demand semantic information set to obtain multiple target semantic categories; Based on the pre-learned mapping relationship between the semantic categories and the resource demand information in the target service field, map the multiple target semantic categories to obtain the first user's potential multi-dimensional resource demand information.

4. The method according to claim 3, wherein It also includes: Obtain a sample data set in the target service field, where the sample data set includes multiple sample portrait data, the sample resource demand semantic information corresponding to each sample portrait data, and the sample semantic category corresponding to each sample resource demand semantic information; Input the multiple sample portrait data into an initial resource demand analysis model, and perform semantic understanding on the multiple sample portrait data from the resource demand dimension to obtain intermediate resource demand semantic information; Perform semantic classification on the intermediate resource demand semantic information to obtain multiple intermediate semantic categories, and learn the mapping relationship between the intermediate semantic categories and the intermediate resource demand semantic information; Based on the mapping relationship, map the multiple intermediate semantic categories to obtain intermediate resource demand information; Calculate a model loss function based on the intermediate resource demand semantic information and the sample resource demand semantic information, and the intermediate semantic categories and the sample semantic categories. When the model loss function does not meet the model training termination condition, continue to train the initial resource demand analysis model until the model loss function meets the model training termination condition to obtain the target resource demand analysis model.

5. The method according to claim 4, wherein Calculating the model loss function based on the intermediate resource demand semantic information and the sample resource demand semantic information, and the intermediate semantic categories and the sample semantic categories includes: Calculate a first loss function between the intermediate resource demand semantic information and the sample resource demand semantic information, and calculate a second loss function between the intermediate semantic categories and the sample semantic categories, both as the model loss function; Or Calculate a first loss function between the intermediate resource demand semantic information and the sample resource demand semantic information, and calculate a second loss function between the intermediate semantic categories and the sample semantic categories, and perform a weighted sum of the first loss function and the second loss function to obtain the model loss function.

6. The method according to claim 1, characterized in that, Each resource configuration information has its own applicable conditions; input the initial portrait data, the depth portrait data, the multi-dimensional resource requirement information, and the recommendation conditions of various resource configuration information into the AI resource information recommendation model. Based on the multi-dimensional resource requirement information and the recommendation conditions of the resource configuration information, select the first target resource configuration information from various resource configuration information, including: Input the multi-dimensional resource requirement information, the recommendation conditions and applicable conditions of each resource configuration information into the AI resource information recommendation model, and perform semantic matching between the resource requirement information in multiple dimensions and the applicable conditions of each resource configuration information to determine the target applicable conditions that are semantically matched with the multi-dimensional resource requirement information; Use the resource configuration information with the target applicable conditions among the various resource configuration information as the candidate resource configuration information; Based on the recommendation conditions of the resource configuration information and the multi-dimensional resource requirement information, select the first target resource configuration information from the candidate resource configuration information.

7. The method according to claim 6, wherein There are multiple recommendation conditions for the resource configuration information. Based on the recommendation conditions of the resource configuration information and the multi-dimensional resource requirement information, select the first target resource configuration information from the candidate resource configuration information, including: Group the various resource configuration information based on the recommendation conditions of each resource configuration information to obtain an initial resource configuration information set adapted to the recommendation conditions of each resource configuration information; For each initial resource configuration information set, analyze the local adaptation degree between each resource configuration information in the initial resource configuration information set and the resource requirement information in each dimension of the multi-dimensional resource requirement information from the service content dimension, calculate the overall adaptation degree according to the local adaptation degree between each resource configuration information and the resource requirement information in each dimension of the multi-dimensional resource requirement information, and use the resource configuration information with the overall adaptation degree greater than the corresponding threshold as the first target resource configuration information under the recommendation conditions of this resource configuration information.

8. The method according to claim 7, wherein The multi-dimensional resource requirement information includes: the attribute information of the first user, the level information of the budget requirement, and the service requirement information. The service requirement information includes: the basic service requirement, the core service requirement, and the service requirement duration; the recommendation conditions of the resource allocation information include the recommendation conditions of the optimal resource allocation information, the recommendation conditions of the medium resource allocation information, and the recommendation conditions of the guaranteed resource allocation information. The recommendation conditions of the optimal resource allocation information are used to determine the resource allocation information with a high budget level and meeting the service requirement information. The recommendation conditions of the medium resource allocation information are used to determine the resource allocation information with a low budget level, meeting the core service requirement and its service requirement duration. The recommendation conditions of the guaranteed resource allocation information are used to determine the resource allocation information meeting the basic service requirement and its service requirement duration; then, for each initial resource allocation information set, analyze the local fitness degree of each resource allocation information in the initial resource allocation information set with each dimension of resource requirement information in the multi-dimensional resource requirement information from the service content dimension, calculate the overall fitness degree based on the local fitness degree of each resource allocation information with each dimension of resource requirement information in the multi-dimensional resource requirement information, and use the resource allocation information with the overall fitness degree greater than the corresponding threshold as the first target resource allocation information under the recommendation conditions of this resource allocation information, including: For the initial resource allocation information set under the recommendation conditions of the optimal resource allocation information, analyze the multiple first local fitness degrees of each resource allocation information in the initial resource allocation information set in the dimensions of the level of budget requirement, basic service requirement, core service requirement, and service requirement duration respectively; calculate the first overall fitness degree based on the multiple first local fitness degrees; use the resource allocation information corresponding to the first overall fitness degree greater than the first threshold as the first target resource allocation information under the recommendation conditions of the optimal resource allocation information; For the initial resource allocation information set under the recommendation conditions of the medium resource allocation information, analyze the multiple second local fitness degrees of each resource allocation information in the initial resource allocation information set in the dimensions of the level of budget requirement, core service requirement, and service requirement duration respectively; calculate the second overall fitness degree based on the multiple second local fitness degrees; use the resource allocation information corresponding to the second overall fitness degree greater than the second threshold as the first target resource allocation information under the recommendation conditions of the medium resource allocation information; For the initial resource allocation information set under the recommendation conditions of the guaranteed resource allocation information, analyze the multiple third local fitness degrees of each resource allocation information in the initial resource allocation information set in the dimensions of the level of budget requirement, basic service requirement, and service requirement duration respectively; calculate the third overall fitness degree based on the multiple third local fitness degrees; use the resource allocation information corresponding to the third overall fitness degree greater than the third threshold as the first target resource allocation information under the recommendation conditions of the guaranteed resource allocation information.

9. The method according to any one of claims 1-8, characterized in that, Generate the recommendation reason information for the first target resource allocation information, including: Generate recommendation reason information of the service requirement type based on the service requirement indicated by the multi-dimensional resource requirement information and the configured service represented by the configuration content of the first target resource configuration information; Generate recommendation reason information of the budget type based on the budget requirement indicated by the multi-dimensional resource requirement information and the configured price represented by the configuration content of the first target resource configuration information; Integrate the recommendation reason information of the service requirement type and the recommendation reason information of the budget type to generate the recommendation reason information of the first target resource configuration information.

10. The method according to claim 9, characterized in that, It further includes: Determine a second user from historical users, where the fitness degree of the multi-dimensional resource requirement information of the second user and the multi-dimensional resource requirement information of the first user is greater than a fourth threshold and the evaluation level of the second target resource configuration information recommended and purchased by the target service personnel to the second user is higher than a fifth threshold; Correspondingly, generating the recommendation reason information of the first target resource configuration information includes: Generate recommendation reason information of the service requirement type based on the service requirement indicated by the multi-dimensional resource requirement information and the configured service represented by the configuration content of the first target resource configuration information; Generate recommendation reason information of the budget type based on the budget requirement indicated by the multi-dimensional resource requirement information and the configured price represented by the configuration content of the first target resource configuration information; generate recommendation reason information of the historical evaluation type based on the historical evaluation information indicated by the multi-dimensional requirement information, the purchased second target resource configuration information, and the evaluation level of the purchased second target service of the second user; integrate the recommendation reason information of the service requirement type, the recommendation reason information of the budget type, and the recommendation reason information of the historical evaluation type to generate the recommendation reason information of the first target resource configuration information.

11. The method according to claim 10, wherein Generate the script information for recommending the first target resource configuration information to the first user based on the recommendation reason information based on the language style information, including: Generate the script information based on the language style information and the recommendation reason information for recommending the first target resource configuration information to the first user.

12. An electronic device, characterized in that, It includes: A memory and a processor; The memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the method according to any one of claims 1-11.

13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the processor is caused to implement the steps in the method according to any one of claims 1-11.

14. A computer program product, characterized in that, The computer program product includes computer programs / instructions, and when the computer programs / instructions are executed by the processor, the processor is caused to be able to implement the steps in the method according to any one of claims 1-11.

Images