Human resource outsourcing customer service information processing method based on third-party communication tool

Abstract

The invention discloses a human resource outsourcing customer service information processing method based on a third-party communication tool. The method is realized based on a human resource outsourcing service system, a third-party communication tool is carried in the human resource outsourcing service system, and employee position information and employee salary information of a plurality of service object enterprises and ID information of employees in the third-party communication tool are stored in the human resource outsourcing service system; the human resource outsourcing customer service information processing method based on the third-party communication tool comprises the following steps: after an employee in a service object enterprise sends consultation information to a customer service account of a human resource outsourcing service system through the third-party communication tool, responding to the consultation information; and the human resource outsourcing service system automatically obtains the ID of the employee in the third-party communication tool and determines that the employee belongs to a first branch company under the first enterprise group. According to the embodiment of the invention, the reply efficiency and accuracy of a human resource outsourcing service enterprise customer service to a customer enterprise employee consultation problem can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet, and also relates to the technical fields of communication and artificial intelligence, in particular to a human resource outsourcing customer service information processing method based on a third-party communication tool, a human resource outsourcing service system, equipment, a program product and a storage medium. BACKGROUND

[0002] In the current enterprise management mode, enterprise employees can consult problems such as enterprise policies, welfare treatment, etc. to enterprise artificial customer service through an instant messaging tool, and the artificial customer service can provide detailed replies for the employees.

[0003] Human resource outsourcing refers to using resources outside an organization to more economically and effectively solve the work involved in human resource activities inside the organization. Human resource outsourcing enterprises provide various human resource outsourcing services for customer enterprises (service objects), including human resource planning, system design and innovation, process integration, employee satisfaction survey, salary survey and scheme design, training work, labor arbitration, employee relations, enterprise culture design, etc. During the service period, the employees of the customer enterprise can consult some salary problems to the customer service of the human resource outsourcing enterprise through a third-party communication tool.

[0004] However, in practice, this mode also has some limitations. In one case, when there is a concentrated influx of consultation demand in a short period of time, the traditional response mode highly dependent on artificial customer service is difficult to respond in time, resulting in delayed response and decreased service experience. In another case, the welfare policies of enterprises in different regions related to salary problems are often updated and unsynchronized, and the artificial customer service is difficult to master all changes in real time, which is easy to cause inaccurate or inconsistent reply information, forming an information gap. Sometimes, the customer service personnel need to manually search for welfare policy documents, which not only is inefficient, but also cannot guarantee the accuracy and completeness of the search results, affecting the reply quality and user satisfaction. SUMMARY

[0005] Therefore, the embodiments of the present application provide a human resource outsourcing customer service information processing method based on a third-party communication tool, a human resource outsourcing service system, an electronic device, a computer readable storage medium and a computer program product, which solve at least one technical problem.

[0006] This application provides a method for processing customer service information in human resource outsourcing based on a third-party communication tool. The method is implemented based on a human resource outsourcing service system, which is equipped with a third-party communication tool and stores employee job information, employee salary information, and employee ID information in the third-party communication tool for multiple service recipient companies. The method for processing customer service information in human resource outsourcing based on a third-party communication tool includes: after an employee in a service recipient company sends an inquiry to the customer service account of the human resource outsourcing service system through the third-party communication tool, in response to the inquiry, the human resource outsourcing service system automatically obtains the employee's ID in the third-party communication tool and determines that the employee belongs to the first branch of the first enterprise group. If the inquiry is related to the company's compensation system, the human resources outsourcing service system automatically accesses the compensation system information database of the first corporate group and determines the sub-information database corresponding to the first branch company within the compensation system information database. The corporate group's compensation system information database stores sub-information databases of the compensation systems of each branch company under the corporate group. Based on the geographical location of the first branch company, the human resources outsourcing service system automatically queries the public welfare policy information corresponding to that geographical location. The public welfare policies in different locations are updated and published by the local functional departments. Based on the sub-information database and / or the public welfare policy information, the human resources outsourcing service system generates multiple response texts for the inquiry and displays them in the chat window of the customer service account for human customer service to select from. The selected response text is then sent to the current employee.

[0007] Optionally, according to the method of this application embodiment, the human resources outsourcing service system generates multiple response texts for the consultation information based on the sub-information database and / or the public welfare policy information, including: if the consultation information includes at least one of salary issues, leave issues, and social security issues, then at least a first response text is generated based on the sub-information database, at least a second response text is generated based on the public welfare policy information, and at least a third response text is generated based on the content of the first response text and the content of the second response text, wherein at least the first response text, at least the second response text, and at least the third response text constitute the multiple response texts.

[0008] Optionally, the method according to the embodiments of this application further includes: if the content of the at least first response text contradicts the content of the at least second response text, issuing a prompt in the chat window of the customer service account, and simultaneously displaying the reason for the contradiction in the text content.

[0009] Optionally, the method according to the embodiments of this application further includes: displaying the source link and publication date of the public welfare policy information involved in generating the response text in the chat window of the customer service account.

[0010] Optionally, according to the method of this application embodiment, after generating multiple response texts, the method further includes: the human resources outsourcing service system prioritizing the generated multiple response texts based on the current employee's job information and historical consultation records.

[0011] Optionally, according to the method of this application embodiment, after the human customer service sends the selected response text to the employee, the method further includes: the human resources outsourcing service system recording the question-and-answer context of the consultation session as training corpus data for the system's question-and-answer model.

[0012] This application provides a human resources outsourcing service system. The system includes a third-party communication tool and stores employee job information, salary information, and employee ID information from multiple client companies via the third-party communication tool. The system comprises: a response module, used to automatically retrieve the employee's ID from the third-party communication tool and determine if the employee belongs to the first branch of a first enterprise group when an employee from a client company sends an inquiry to the system's customer service account via the third-party communication tool; and an access and confirmation module, used to, if the inquiry is related to the company's compensation system, automatically retrieve the employee's ID from the third-party communication tool and determine if the employee belongs to the first branch of a first enterprise group. The system automatically accesses the salary system information database of the first enterprise group and determines the sub-information database corresponding to the first branch in the salary system information database. The salary system information database of the enterprise group stores the sub-information databases of the salary systems of each branch under the enterprise group. The query module is used by the human resources outsourcing service system to automatically query the public welfare policy information corresponding to the geographical location of the first branch. The public welfare policies in different places are updated and published by the local functional departments. The generation module is used by the human resources outsourcing service system to generate multiple response texts for the consultation information based on the sub-information database and / or the public welfare policy information, and display them in the chat window of the customer service account for human customer service to select, and send the selected response texts to the current employee.

[0013] This application provides an electronic device, which includes a processor and a memory storing computer program instructions; the electronic device executes the computer program instructions to implement the method described above.

[0014] This application provides a computer program product, which includes computer program instructions that, when executed, implement the method described above.

[0015] This application provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the method described above.

[0016] The method provided in this application integrates the convenience of third-party communication tools, the structured data of human resource outsourcing service systems, and external public policy information. This not only improves the response speed of customer service and solves the problems of response delay and service experience decline, but also improves the accuracy and timeliness of welfare policy information responses, as well as response quality and user satisfaction, without requiring customer service personnel to manually search for welfare policies. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings of the embodiments of this application will be briefly described below.

[0018] Figure 1 This is a schematic diagram of the system architecture of an embodiment of this application.

[0019] Figure 2 This is a flowchart of a human resources outsourcing customer service information processing method based on a third-party communication tool, according to an embodiment of this application.

[0020] Figure 3 This is a flowchart of the backend data interaction process and a schematic diagram of the chat window of the frontend customer service account, representing an embodiment of this application.

[0021] Figure 4 This is a schematic structural block diagram of the human resources outsourcing service system according to an embodiment of this application.

[0022] Figure 5 This is a schematic diagram of an electronic device used to implement the human resources outsourcing customer service information processing method based on a third-party communication tool according to the embodiments of this application. Detailed Implementation

[0023] The principles and spirit of this application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided to make the principles and spirit of this application clearer and more thorough. The exemplary embodiments provided herein are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0024] Embodiments of this application relate to terminal devices and / or servers. Implementations of this application can be a system, terminal, device, method, computer-readable storage medium, or computer program product, and can be specifically implemented as entirely hardware, entirely software, or a combination of hardware and software. Figure 1This diagram illustrates a system architecture according to an embodiment of the present application, including a terminal device 102 and a server 104. The terminal device 102 may include at least one of the following: a smartphone, tablet computer, laptop computer, desktop computer, smart TV, various wearable devices, augmented reality (AR) devices, virtual reality (VR) devices, etc. A client application, such as an app, mini-program, or browser-based client, can be installed on the terminal device 102. Users can input commands through the client, and the terminal device 102 can send request information containing the commands to the server 104. Upon receiving the request information, the server 104 performs corresponding processing and returns the processing result information to the terminal device 102. The server 104 may be a local server or a cloud server, and may be a single server or a server cluster, etc.

[0025] In this document, the terms "first," "second," "third," etc., are used only in textual descriptions to distinguish one entity (or operation) from another, and do not require or imply any sequential order between these entities (or operations).

[0026] Figure 2 This document illustrates a flowchart of a human resources outsourcing customer service information processing method based on a third-party communication tool, according to an embodiment of this application. The method is implemented using a human resources outsourcing service system, which incorporates a third-party communication tool and stores employee job information, salary information, and employee ID information from multiple client companies within the third-party communication tool. The method includes the following steps:

[0027] S101: After an employee in a service recipient company sends an inquiry to the customer service account of the human resources outsourcing service system through a third-party communication tool, in response to the inquiry, the human resources outsourcing service system automatically obtains the employee's ID in the third-party communication tool and determines that the employee belongs to the first branch of the first enterprise group.

[0028] S102: If the consultation information is related to the company’s compensation system, the human resources outsourcing service system will automatically access the compensation system information database of the first enterprise group and determine the sub-information database corresponding to the first branch in the compensation system information database. The compensation system information database of the enterprise group stores the sub-information databases of the compensation systems of each branch under the enterprise group.

[0029] S103: The human resources outsourcing service system automatically queries the public welfare policy information corresponding to the geographical location of the first branch office. The public welfare policies in different places are updated and published by the local functional departments.

[0030] S104: The human resources outsourcing service system generates multiple response texts for consultation information based on sub-information databases and / or public welfare policy information, and displays them in the chat window of the customer service account for human customer service to select from, and sends the selected response texts to the current employee.

[0031] The human resources outsourcing customer service information processing method proposed in this application integrates the convenience of third-party communication tools, the structured data of the human resources system, and external public policy information, providing an intelligent customer service response assistance method. This method breaks down data barriers between independent systems such as third-party communication tools, human resources information, and external policy databases, and designs an automated workflow. It can automatically trace the organizational structure of the consulting employee based on their identity, accurately locate applicable internal compensation systems and external public welfare policies, and automatically generate highly customized response drafts. Ultimately, through a "human-machine collaboration" model (i.e., system recommendation and human decision-making before sending), it greatly improves the processing efficiency, accuracy, and consistency of human resources outsourcing customer service. The following detailed description, in conjunction with specific embodiments, further illustrates this application.

[0032] First, the implementation process of the method in this application embodiment is described. The execution subject of the human resources outsourcing customer service information processing method proposed in this application embodiment is the human resources outsourcing service system. This system is equipped with third-party communication tools (such as WeChat Work, DingTalk, etc.), which means that the communication interface between customer service and employees is a tool that everyone is familiar with and uses frequently, greatly reducing the threshold for use. This is the basic environment for the realization and promotion of this invention. When an employee in the service recipient company sends consultation information to the customer service account through this third-party communication tool, the human resources outsourcing service system will respond immediately. Its first key technical action is to automatically obtain the employee's unique ID in the third-party communication tool and use the pre-stored association database inside the system to map the ID to its corresponding employee file, thereby determining which specific branch of which enterprise group the employee belongs to, such as "the first branch of the first enterprise group". This "automatic identity recognition and traceability" feature is the starting point and key of the entire process. It avoids the inefficient process of customer service needing to manually ask and verify the employee's basic information repeatedly in the traditional model, laying the foundation for subsequent accurate information retrieval.

[0033] If the inquiry information is related to the company's compensation system (e.g., containing keywords such as "salary," "housing provident fund," and "subsidy"), the system will trigger an automated information retrieval process. Instead of aimlessly searching the entire corporate group's system, it automatically accesses the corporate group's compensation system database based on the previously identified "First Branch Company" identity information, precisely locating the sub-database configured or applicable specifically for that First Branch Company. The corporate group's compensation system database is constructed according to its organizational structure, setting up differentiated sub-databases for branches in different regions and with different natures. This ensures the accuracy of the system query and avoids errors caused by incorrect system application. Next, based on the identified physical location of the First Branch Company (e.g., "Pudong New Area, Shanghai"), the system will automatically initiate a query for external information (public welfare policies). This "automatic query" is a dynamic and proactive technical process, implemented by periodically crawling official website announcements from local human resources and social security, tax, and other functional departments, or by calling standardized government data API interfaces provided by these departments, ensuring that the obtained policy information is the latest and most authoritative. Internal compensation systems and external public welfare policies together constitute a complete set of rules for answering employee inquiries.

[0034] Finally, based on the internal rules in the retrieved "sub-information database" and / or the external rules in the retrieved "public welfare policies," the system performs information fusion and logical operations to generate multiple alternative response texts for the employee's specific question. These texts are presented in the chat window of a human customer service representative for review and selection. The role of the human customer service representative is thus elevated from "information searcher" and "answer editor" to "decision-maker" and "quality gatekeeper," as they only need to select the most appropriate option from the system's intelligent recommendations. This "system-generated, human-selected" model, while ensuring the accuracy and compliance of the answers, greatly reduces the cognitive load on customer service personnel, shortens response time, and improves the service experience.

[0035] Furthermore, in this embodiment, providing employees with consulting information by combining salary information (internal company policy) with public welfare policy information (external regulations) offers several significant advantages. Fundamentally, an employee's actual salary and benefits are not solely determined by the company's internal compensation system, but rather by the combined effect and complex calculations of both internal and external policies. Basic salary and performance bonuses fall under the scope of internal policies, while the contribution base and ratio for pension insurance, medical insurance, and housing provident fund ("five insurances and one fund"), the withholding of personal income tax, and various local subsidies (such as high-temperature subsidies and heating subsidies) are strictly governed by local laws, regulations, and policies. The primary benefit of combining the two is improved accuracy and completeness of the response. If the system only responds with internal salary regulations, it may fail to explain why the housing provident fund is contributed based on a specific base; if it only responds with external policies, employees will not be able to understand additional benefits such as company annuities or supplementary medical insurance. Only by combining the two can employees be provided with a comprehensive and accurate answer. For example, if an employee asks, "Why is my housing provident fund amount X yuan this month?", the system can clearly calculate the result by combining the internally determined contribution base and the upper limit of the contribution ratio announced by the local government. This avoids misunderstandings and doubts caused by fragmented information, thereby greatly improving the credibility and authority of the response.

[0036] Secondly, this integration significantly improves customer service efficiency and user experience. It resolves all potential related questions from employees in one go, avoiding the vortex of back-and-forth questioning. In the traditional model, customer service might first answer questions about basic salary, and then employees might follow up with questions about housing provident fund calculation methods, and then personal income tax. A single consultation could lead to multiple interactions, resulting in low efficiency. The integrated response provided by this solution is equivalent to "anticipating" potential follow-up questions from employees, compressing multiple rounds of dialogue into a single round. This greatly shortens the communication chain, saving valuable time for both employees and customer service, and delivering an efficient and smooth service experience.

[0037] Finally, this mechanism is a crucial link in risk control and compliance assurance. Public welfare policies, especially regulations concerning social security and taxation, are legally mandatory. Enterprises' human resource management must strictly adhere to them. The system automatically queries and applies the latest policies, ensuring that responses and subsequent operations (such as payroll calculations) remain within a compliant framework. This effectively avoids legal and financial risks arising from customer service personnel providing incorrect or non-compliant advice due to a lack of understanding of the latest policies. It proactively and automatically embeds compliance checks into every relevant consultation and response process, building a robust "compliance firewall" for enterprises.

[0038] In summary, the method proposed in this application not only automates and intelligentizes the customer service response process, significantly improving response efficiency and resolving issues of response delays and decreased service experience, but also ensures high accuracy and personalization of response content through precise identity tracing and data association. Furthermore, it ensures the timeliness and compliance of responses by dynamically integrating external policy information; and it optimizes human resource allocation through human-machine collaboration, reducing reliance on the personal experience and memory of customer service personnel, improving the accuracy and timeliness of responses to welfare policy information, as well as response quality and user satisfaction, while also reducing operating costs.

[0039] In some embodiments of this application, optionally, the human resources outsourcing service system generates multiple response texts for consultation information based on a sub-information database and / or public welfare policy information, including: if the consultation information includes at least one of salary issues, leave issues, and social security issues, then at least a first response text is generated based on the sub-information database, at least a second response text is generated based on the public welfare policy information, and at least a third response text is generated based on the content of the first response text and the content of the second response text, wherein at least the first response text, at least the second response text, and at least the third response text constitute multiple response texts.

[0040] In this embodiment, the response text generation mechanism is further refined, improving the accuracy and comprehensiveness of customer service responses through multi-source information fusion. Specifically, when inquiries involve core human resource issues such as salary, leave, or social security, the system does not simply return a single answer. Instead, it generates basic response texts from two dimensions: internal company policies (sub-information database) and external public policies (public welfare policy information). These are then integrated to generate a comprehensive response text. This logic reduces the decision-making burden on human customer service representatives and minimizes the risk of misjudgment.

[0041] For example, suppose an employee of a branch office inquires via WeChat, "How many days of maternity leave are there?" The system first identifies this as a leave-related question, then accesses the branch office's sub-database, extracts the internally mandated paid maternity leave of 120 days, and generates the first response text: "According to company policy, maternity leave is 120 days." Simultaneously, the system queries the local public welfare policy, finding that the local statutory maternity leave is 128 days, and generates the second response text: "The local statutory maternity leave is 128 days." Next, the system compares the two responses and automatically generates a third response text: "Company policy stipulates 120 days of maternity leave, which is less than the statutory 128 days; it is recommended to follow the statutory standard." Finally, these three response texts are displayed side-by-side to customer service, who can choose to send the appropriate response based on the actual situation. This process demonstrates how the system efficiently supports human customer service decision-making through layered processing and data integration.

[0042] Optionally, in some embodiments of this application, it may also include: if the content of at least the first response text contradicts the content of at least the second response text, a prompt is issued in the chat window of the customer service account, and the reason for the contradiction in the text content is displayed.

[0043] This application embodiment establishes a conflict detection and alert mechanism. It anticipates potential inconsistencies (i.e., contradictions) between internal company policies (first response text) and external public policies (second response text). Such contradictions could confuse customer service representatives and lead to incorrect responses. Therefore, this application embodiment goes beyond simply listing a few answers; it possesses intelligent comparison capabilities. Once a contradiction is detected, it proactively alerts customer service, analyzes the reasons for the contradiction, directly reveals potential risks, and guides customer service representatives to make prudent choices. This logic significantly enhances the system's depth of decision support and risk control capabilities.

[0044] Optionally, in some embodiments of this application, it may also include: displaying the source link and publication date of the public welfare policy information involved in generating the response text in the chat window of the customer service account.

[0045] In some embodiments of this application, when generating response text, the system automatically traces the source and publication date of the information fragment, and formats the source as a clickable hyperlink and displays it in the chat window. For example, when the response text references the statement "According to the latest housing provident fund management regulations of this city, the employer's contribution rate is 12%", a link to the original policy page of the "XX City Housing Provident Fund Management Center" official website will be attached below the text, displaying the publication date of the information. This approach has several advantages: First, it empowers employees to trace and verify information; employees can click the link to view the official text, thereby building stronger trust in customer service responses and reducing the burden of explanation on customer service staff. Second, it serves as an employee education tool, guiding employees to study relevant policy texts independently and cultivating their habit of self-service inquiry, potentially reducing the number of inquiries about similar basic issues in the future. Third, attaching an authoritative link when sending the final message to human customer service greatly enhances the professionalism and persuasiveness of the response, reflecting a high degree of rigor and transparency in the service.

[0046] Optionally, in some embodiments of this application, the processing of human resource outsourcing customer service information based on third-party communication tools may further include the following steps:

[0047] Without human customer service involvement, multiple generated response texts are sent directly to company employees via chat.

[0048] In this embodiment, the system first assesses the type and complexity of the inquiry, as well as the certainty of the generated response text. For example, for factual questions with clear, single answers, such as "What is the payday for this month?" or "What is the local medical insurance contribution rate?", all the response texts generated by the system will essentially be highly similar. In this case, bypassing the manual review process and sending the response automatically can achieve a response time in seconds, greatly improving processing efficiency and reducing the labor costs for human resource outsourcing service providers.

[0049] Optionally, the method according to embodiments of this application further includes, before generating the response text:

[0050] The system filters relevant content from the retrieved sub-information databases and / or public welfare policy information for sensitive words, and generates multiple response questions based on the filtered information.

[0051] This implementation method is based on a continuously updated sensitive word database, which may contain personal privacy data (such as specific employee names, ID numbers, and bank account numbers), core corporate secrets (such as undisclosed financial data and specific salary calculation formulas), or inappropriate expressions. After retrieving the original text of internal salary systems and external policies, the system does not directly use fragments as answers. Instead, it first processes the information through filtering rules. For example, it replaces the specific amount in "Your pre-tax salary is XXX yuan" with "Your pre-tax salary details can be queried through secure channel XXX," or identifies and blocks paragraphs in the original policy text that involve details of corporate declarations and are not suitable for disclosure to all employees. After filtering, the system generates a compliant response text based on the filtered information. This preprocessing step proactively avoids the significant risk of unintentionally disclosing personal privacy or corporate trade secrets, providing a crucial security barrier for the entire automated customer service process. This allows the present invention to ensure information security and compliance while pursuing efficiency.

[0052] Optionally, according to the method of this application embodiment, after generating multiple response texts, the method further includes: the human resources outsourcing service system prioritizing the generated multiple response texts based on the current employee's job information and historical consultation records.

[0053] In this embodiment, the human resources outsourcing service system does not randomly list multiple generated response texts to customer service. Instead, it accesses the employee's personal file to obtain their job information (e.g., "Senior Engineer" or "Sales Manager"), as different positions may be subject to different salary details or subsidy standards. Simultaneously, the system queries the employee's historical consultation records to understand their past concerns. Then, the system uses a sorting algorithm, for example, placing response texts that better match the job title or are more relevant to past consultation questions at the top of the list. For instance, if an executive inquires about year-end bonuses, their solution may differ from that of a regular employee, and the system will prioritize displaying the executive's version of the answer. Similarly, if an employee repeatedly inquires about medical insurance, the system may prioritize displaying policy interpretations related to medical insurance in their next inquiry. This feature further improves the efficiency of human-computer interaction, allowing customer service representatives to see the most likely options immediately, reducing screening time and demonstrating the system's deep level of intelligence.

[0054] Optionally, according to the method of this application embodiment, after the human customer service sends the selected response text to the employee, the method further includes: the human resources outsourcing service system recording the question and answer context of the consultation session as training corpus data for the system's question and answer model.

[0055] After a human customer service representative sends the selected response text to an employee, the HR outsourcing service system records the question and answer content of the consultation, the selected response text, and the final text sent. Based on historical data, a machine learning model is used to optimize the quality of subsequent response text generation. Thus, the customer service information processing method proposed in this application not only handles single consultations but also treats each customer service interaction as a learning opportunity. After each session, the system automatically records a data package, including: the employee's original consultation question, all candidate response texts generated by the system, the text ultimately selected and sent by the human customer service representative (this is considered a "positive sample"), and sometimes even manual modifications made by the customer service representative to the system-generated text. These historical records are continuously accumulated, forming a training dataset.

[0056] Subsequently, the machine learning models (such as natural language processing-based text generation models) set up in the system will be trained periodically or based on a certain amount of data using this dataset. The training goal of the model is to learn the decision preferences of human customer service representatives, such as which wording is more favored, which information is most critical for specific questions, and how to more naturally integrate internal policies and external regulations into the text. Through continuous learning, the response texts generated by the model will become increasingly accurate, increasingly in line with the expectations of human customer service representatives, and may even reduce the number of options that need to be provided, thereby achieving continuous optimization of the system.

[0057] The implementation methods and advantages of the embodiments of this application have been described above through multiple examples. The specific processing procedures of the embodiments of this application are described in detail below with reference to specific examples.

[0058] Figure 3 Taking WeChat Work as a third-party communication tool as an example, this paper describes the data interaction process flowchart 301 between the backend WeChat Work, the AI ​​customer service provided by the human resources outsourcing service system, the human resources outsourcing service system, and the data mining group interface, as well as the chat toolbar 302 and the chat window 303 displayed in the chat window of the customer service chat account. Figure 3 The data interaction process flowchart 301 shows that the employee's inquiry is forwarded to the customer service account (AI customer service) through the WeChat Work service API. The AI ​​customer service first determines whether the message is the first message. If it is the first message, it needs to obtain the employee's information through the human resources outsourcing service system (HRO system) based on the employee's WeChat Work account, such as which company the employee is from, what their position is, etc.

[0059] If this is not the first question asked by the employee, the employee's information can be obtained from the historical records. In this case, the question and the employee's basic information are forwarded directly to the data mining team. The data mining team can perform intent recognition to determine whether it is a consultation question. Then, by extracting key information, one or more structured database query statements are generated. By executing the query statement, the corresponding response data is retrieved from the public welfare policy information database.

[0060] The data mining team sends the retrieved response data and inquiries to the AI ​​customer service team. The customer service team then performs intent recognition. If it's an inquiry, the system provides an answer directly through the AI ​​agent. Alternatively, after determining it's an inquiry, the system checks if it has been transferred to a human agent. If not, it automatically replies; if so, it assigns a customer service representative, obtains their information, and provides human assistance. The retrieved information will be displayed in the custom chat toolbar 302 of WeChat Work, which also shows relevant policy links. If information in the custom chat toolbar 302 is selected, a human customer service representative can copy and paste it into the text input field of the chat window 303 between the customer service representative and the employee, and then send it to the employee making the inquiry via chat.

[0061] Correspondingly, this application also provides a human resources outsourcing service system, for reference. Figure 4 The human resources outsourcing service system incorporates third-party communication tools and stores employee job information, salary information, and employee ID information from multiple client companies within these third-party communication tools. The human resources outsourcing service system includes:

[0062] The response module 110 is used to respond to the inquiry information sent by an employee of the service recipient company to the customer service account of the human resources outsourcing service system through a third-party communication tool. The human resources outsourcing service system automatically obtains the employee's ID in the third-party communication tool and determines that the employee belongs to the first branch of the first enterprise group.

[0063] The access and confirmation module 120 is used to automatically access the salary system information database of the first enterprise group and determine the sub-information database corresponding to the first branch in the salary system information database if the consultation information is related to the enterprise's salary system. The salary system information database of the enterprise group stores the sub-information databases of the salary systems of each branch under the enterprise group.

[0064] The query module 130 is used by the human resources outsourcing service system to automatically query public welfare policy information corresponding to the geographical location of the first branch. The public welfare policies in different places are updated and published by the local functional departments.

[0065] The generation module 140 is used by the human resources outsourcing service system to generate multiple response texts for consultation information based on sub-information databases and / or public welfare policy information, and display them in the chat window of the customer service account for human customer service to select, and send the selected response texts to the current employee.

[0066] Based on at least one of the above embodiments, this application also provides a smart terminal device, specifically a smartphone, which includes a processor and a memory storing computer program instructions. When the processor executes the computer program instructions, the smartphone implements the method corresponding to the embodiments of this application.

[0067] Based on at least one of the above embodiments, the electronic device in the embodiments of this application may be a user terminal device, a server, other computing devices, or a cloud server. Figure 5 The diagram illustrates the hardware structure of an electronic device according to an embodiment of this application. The electronic device may include a processor 601 and a memory 602 storing computer program instructions. The processor 601 reads and executes the computer program instructions stored in the memory 602 to implement the process or function of any of the methods described above.

[0068] Specifically, processor 601 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Memory 602 may include a mass storage device for data or instructions. For example, memory 602 may be at least one of the following: a hard disk drive (HDD), read-only memory (ROM), random access memory (RAM), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, universal serial bus (USB) drive, or other physical / tangible memory storage device. Alternatively, memory 602 may include removable or non-removable (or fixed) media. Furthermore, memory 602 may be internal or external to the integrated gateway disaster recovery device. Memory 602 may be non-volatile solid-state memory. In other words, typically memory 602 includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in the methods of the embodiments of this application.

[0069] As an example, Figure 5 The illustrated electronic device may also include a communication interface 603 and a bus 610. The processor 601, memory 602, and communication interface 603 are connected via bus 610 and communicate with each other. Bus 610 may include hardware, software, or both, and may couple components of an online data traffic metering device together. The bus may include at least one of the following: Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) bus, Infinite Bandwidth Interconnect, Low Pin Count (LPC) bus, memory bus, Microchannel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus, or other suitable buses. Bus 610 may include one or more buses. Although specific buses are described or shown in the embodiments of this application, any suitable bus or interconnection method is contemplated in the embodiments of this application.

[0070] In conjunction with the methods in the above embodiments, this application also provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the process or function of any of the methods in the above embodiments.

[0071] This application also provides a computer program product that stores computer program instructions, which, when executed by a processor, implement the process or function of any of the methods described above.

[0072] The flowcharts and / or block diagrams of methods, terminals, systems, and computer program products according to embodiments of this application have been exemplarily described above, and related aspects have been described. It should be understood that each block or combination thereof in the flowcharts and / or block diagrams may be implemented by computer program instructions, by dedicated hardware performing a specified function or action, or by a combination of dedicated hardware and computer instructions. For example, these computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to form a machine such that these instructions, executed via such processor, enable the implementation of the function / action specified in each block or combination thereof in the flowcharts and / or block diagrams. Such a processor may be a general-purpose processor, a dedicated processor, a special-purpose application processor, or a field-programmable logic circuit.

[0073] The functional blocks shown in the structural block diagrams of this application can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc.; when implemented in software, they are programs or code segments used to perform the required tasks. Programs or code segments can be stored in memory or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. Code segments can be downloaded via computer networks such as the Internet or intranets.

[0074] It should be noted that this application is not limited to the specific configurations and processes described above or shown in the figures. The above descriptions are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the described systems, devices, terminals, modules, or units can be referred to the corresponding processes in the method embodiments, and need not be repeated here. It should be understood that the scope of protection of this application is not limited thereto. Any equivalent modifications or substitutions that can be conceived by those skilled in the art within the scope of the technology disclosed in this application should be covered within the scope of protection of this patent application.

Claims

1. A method for processing customer service information in human resource outsourcing based on a third-party communication tool, the method being implemented based on a human resource outsourcing service system, characterized in that... The human resources outsourcing service system is equipped with third-party communication tools, and the human resources outsourcing service system stores employee job information, employee salary information, and employee ID information in the third-party communication tools of multiple service recipient companies; The method for processing customer service information in human resource outsourcing based on third-party communication tools includes: After an employee in a service recipient company sends an inquiry to the customer service account of the human resources outsourcing service system through the third-party communication tool, the human resources outsourcing service system automatically obtains the employee's ID in the third-party communication tool and determines that the employee belongs to the first branch of the first enterprise group in response to the inquiry. If the consultation information is related to the company's compensation system, the human resources outsourcing service system will automatically access the compensation system information database of the first enterprise group and determine the sub-information database corresponding to the first branch in the compensation system information database. The enterprise group's compensation system information database stores the sub-information databases of the compensation systems of each branch under the enterprise group. The human resources outsourcing service system automatically queries the public welfare policy information corresponding to the geographical location of the first branch office. The public welfare policies in different places are updated and published by the local functional departments. The human resources outsourcing service system generates multiple response texts for the consultation information based on the sub-information database and / or the public welfare policy information, and displays them in the chat window of the customer service account for human customer service to select from, and sends the selected response texts to the current employee.

2. The method according to claim 1, characterized in that, The human resources outsourcing service system generates multiple response texts for the consultation information based on the sub-information database and / or the public welfare policy information, including: if the consultation information includes at least one of salary issues, leave issues, and social security issues, then at least a first response text is generated based on the sub-information database, at least a second response text is generated based on the public welfare policy information, and at least a third response text is generated based on the content of the first response text and the content of the second response text, wherein at least the first response text, at least the second response text, and at least the third response text constitute the multiple response texts.

3. The method according to claim 2, characterized in that, Also includes: If the content of at least the first response text contradicts the content of at least the second response text, a prompt will be issued in the chat window of the customer service account, and the reason for the contradiction in the text content will be displayed.

4. The method according to claim 3, characterized in that, Also includes: The chat window of the customer service account displays the source link and publication date of the public welfare policy information involved in generating the response text.

5. The method according to claim 1, characterized in that, After generating multiple response texts, the method further includes: the human resources outsourcing service system prioritizing the generated multiple response texts based on the current employee's job information and historical consultation records.

6. The method according to claim 1, characterized in that, After the human customer service representative sends the selected response text to an employee, the method further includes: The human resources outsourcing service system records the question-and-answer context of the consultation session, which serves as training corpus data for the system's question-and-answer model.

7. A human resources outsourcing service system, characterized in that, The human resources outsourcing service system is equipped with third-party communication tools, and the human resources outsourcing service system stores employee job information, employee salary information, and employee ID information in the third-party communication tools of multiple service recipient companies; The human resources outsourcing service system includes: The response module is used to respond to the inquiry information sent by an employee of the service recipient company to the customer service account of the human resources outsourcing service system through the third-party communication tool. The human resources outsourcing service system automatically obtains the employee's ID in the third-party communication tool and determines that the employee belongs to the first branch of the first enterprise group. The access and confirmation module is used so that if the consultation information is related to the company's compensation system, the human resources outsourcing service system can automatically access the compensation system information database of the first enterprise group and determine the sub-information database corresponding to the first branch in the compensation system information database. The compensation system information database of the enterprise group stores the sub-information databases of the compensation systems of each branch under the enterprise group. The query module is used by the human resources outsourcing service system to automatically query public welfare policy information corresponding to the geographical location of the first branch. The public welfare policies in different places are updated and published by the local functional departments. The generation module is used by the human resources outsourcing service system to generate multiple response texts for the consultation information based on the sub-information database and / or the public welfare policy information, and display them in the chat window of the customer service account for human customer service to select, and send the selected response texts to the current employee.

8. An electronic device, characterized in that, The electronic device is a terminal device or a server. The electronic device includes a processor and a memory storing computer program instructions. When the electronic device executes the computer program instructions, it implements the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, It includes computer program instructions that, when executed, implement the method as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed, implement the method as described in any one of claims 1-5.

Images