Information display method, clue record generation method and corresponding devices

Abstract

The embodiment of the invention discloses an information display method, a clue record generation method and corresponding devices. The information display method comprises the steps that a first interface is displayed, the first interface comprises a call record of a user bound with a client side, and the call record is obtained after semantic analysis is conducted on call content of the user and the client; in response to triggering an operation of generating a clue record for the target call record, displaying a second interface, and displaying a structured feature of the target call record on the second interface, the structured feature of the target call record being obtained by performing structured analysis on the target call record; and in response to triggering an operation of creating a clue record for the target call record, sending a clue record creation request to the server side to create the clue record, the clue record comprising the structured features of the target call record, and the structured features of the target call record comprising the customer feature data. According to the invention, the intelligent degree of customer relationship management by the CRM and the efficiency of sales personnel can be improved.

Description

Technical Field

[0001] This application relates to the field of computer application technology, and in particular to an information display method, a clue record generation method, and a corresponding device. Background Technology

[0002] To help businesses provide better service to their customers, CRM (Customer Relationship Management) systems have gradually emerged. However, current CRM systems are mainly used to display real-time sales data. For pre-sales customer relationship management, it still mainly relies on manual maintenance by users (such as salespeople), which is both low in intelligence and inefficient. Summary of the Invention

[0003] In view of this, this application provides an information display method, a lead recording generation method, and a corresponding device to improve the intelligence of CRM in pre-sales customer relationship management and increase the efficiency of sales personnel.

[0004] This application provides the following solution: An information display method, applied to a client of a customer relationship management system, the method comprising: The system displays a first interface, which includes call records of the user bound to the client. These call records are obtained by semantic analysis of the call content between the user and the client. In response to the operation of generating clue records for the target call record, a second interface is displayed, and the structured features of the target call record are displayed on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record. In response to triggering the operation of creating a lead record for the target call record, a lead record creation request is sent to the server to create the lead record. The lead record includes the structured features of the target call record, and the structured features of the target call record include customer feature data.

[0005] Optionally, before displaying the first interface, the following may also be included: A third interface is displayed, which includes an outbound call entry component; In response to the operation of triggering the outbound call entry component, the first interface is displayed. The first interface also includes an outbound call component, which is used to trigger a voice call between the user and the customer.

[0006] Optionally, the first interface includes at least one first card component, and each first card component corresponds to a call record; In response to an operation that triggers one of the first card components, a details interface of the call record corresponding to the triggered first card component is displayed. The details interface includes at least one of the call record's call time, duration, content text, summary information, and tag information. The label information mentioned therein includes at least one of customer intent labels, customer sentiment labels, customer category labels, and labels related to the target.

[0007] Optionally, displaying the structured features of the target call record on the second interface includes: displaying the structured features of the target call record on the second interface through an editable component; and displaying the edited structured features of the target call record in response to an editing operation on the structured features of the target call record through the editable component. The step of sending a lead record creation request to the server in response to triggering the operation of creating a lead record for the target call record includes: in response to triggering the operation of the lead record creation component on the second interface, sending a lead record creation request to the server using the structured features of the target call record currently displayed on the second interface.

[0008] Optionally, the method further includes: In response to the operation of triggering the viewing of clue records, a fourth interface is displayed and at least one second card component is displayed on the fourth interface, each second card component corresponding to a clue record obtained from the server. In response to an operation that triggers one of the second card components, a details interface for the lead record corresponding to the triggered second card component is displayed. The details interface includes at least one of lead record quality information, maintenance status information, customer characteristic data, and customer intent summary.

[0009] Optionally, the second card component displays an exit component corresponding to the clue record; the method further includes: In response to the operation of triggering the sign-out component, if the location of the client is consistent with the customer location in the customer feature data contained in the lead record corresponding to the triggered sign-out component, then the maintenance status information of the lead record corresponding to the triggered sign-out component is updated.

[0010] Secondly, a method for generating lead records is provided, applied to the server side of a customer relationship management system, the method comprising: Obtain the content of user and customer calls; Semantic analysis is performed on the call content to obtain the user's call records; The target call record in the call log is subjected to structured analysis to obtain the structured features of the target call record; In response to a lead record creation request for the target call record, a lead record is created and stored, the lead record including structured features of the target call record, the structured features of the target call record including customer feature data.

[0011] Optionally, the step of performing semantic analysis on the call content to obtain the user's call records includes: The large language model is invoked to identify customer intent, analyze customer sentiment, and perform semantic analysis based on the call content. Based on the results of the semantic analysis, a summary of the call content, customer category, and the target involved are obtained; The call log includes at least one of the following: call time, duration, text content of the call, summary information, and tag information; The tagging information includes at least one of customer intent tags, customer sentiment tags, customer category tags, and relevant target tags.

[0012] Optionally, the step of performing structured analysis on the target call record in the call log to obtain the structured features of the target call record includes: The target call record is subjected to entity and event extraction of a preset type to obtain the structured features of the target call record. The structured features of the target call record include customer feature data, or the structured features of the target call record include customer feature data and customer intention summary. The customer characteristic data mentioned above includes customer attribute data and demand data.

[0013] Optionally, the creation and storage of clue records includes: If the quality of the requested lead record meets the preset quality requirements, then the lead record is created and stored in the lead record database; If the quality of the requested lead record does not meet the preset quality requirements, the structured features of the target call record will be imported into the nurturing pool. The quality of the lead records is based on the customer intent and emotional inclination of the target call records.

[0014] Thirdly, an information display device is provided, the device comprising: The interface display unit is configured to display a first interface, which includes the call records of the user bound to the client. The call records are obtained by semantic analysis of the call content between the user and the client. The operation listening unit is configured to listen for operations on the interface. The interface display unit is further configured to respond to the operation monitoring unit detecting the operation that triggers the generation of clue records for the target call record, display a second interface, and display the structured features of the target call record on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record. The request sending unit is configured to send a lead record creation request to the server to create a lead record in response to the operation listening unit detecting an operation that triggers the creation of a lead record for the target call record. The lead record includes the structured features of the target call record, and the structured features of the target call record include customer feature data.

[0015] Fourthly, a clue recording generation device is provided, the device comprising: The content acquisition unit is configured to acquire the content of the user's call with the customer; The content analysis unit is configured to perform semantic analysis on the call content to obtain the user's call records; and to perform structured analysis on target call records in the call records to obtain the structured features of the target call records. The request receiving unit is configured to receive a clue record creation request for the target call record; A lead record creation unit is configured to create and store a lead record in response to the lead record creation request. The lead record includes structured features of the target call record, and the structured features of the target call record include customer feature data.

[0016] Fifthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first and second aspects above.

[0017] Sixthly, an electronic device is provided, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any one of the first and second aspects above.

[0018] A seventh aspect provides a computer program product comprising a computer program that, when executed by a processor, implements the steps of the method described in any one of the first and second aspects above.

[0019] According to the specific embodiments provided in this application, the following technical effects are disclosed: 1) The method provided in this application enables the semantic analysis of call records obtained from the call content between the user and the customer, and the structured analysis of the target call records in the call records to automatically display the structured features of the target call records to the user. In response to triggering the operation of creating lead records for the target call records, the automatic creation of lead records is realized. This method can automatically create target call records such as customer feature data. Compared with the manual recording method, both the level of intelligence and the efficiency of users are effectively improved.

[0020] 2) This application allows users to access the first interface displaying call logs via the outbound call entry component on the third interface, and users can trigger voice calls with customers through the outbound call component on the first interface. This integration of call log display with the outbound call component standardizes the outbound call process, requiring calls to be initiated through the CRM system, and also makes it easier for users to quickly initiate outbound calls to customers based on call logs, resulting in higher efficiency.

[0021] 3) This application can use a first card component to correspond to call records in the first interface to provide a lightweight overview of the call records. After the first card component is triggered, the structured information of outbound calls can be further displayed on the details interface of the call records. Customer value can be extracted in the form of tags, and core content can be extracted in the form of summaries, thereby helping users to quickly obtain valuable information and make decisions efficiently.

[0022] 4) In this application, the second interface can display the structured features of the target call record through editable components, which makes it convenient for users to flexibly and efficiently edit the structured features of the target call record, and quickly initiate a clue record creation request based on the edited structured features of the target call record.

[0023] 5) For existing lead records, they can be displayed through the second card component in the fourth interface. When the second card component is triggered, the details of the lead record can be displayed, such as at least one of the following: lead record quality information, maintenance status information, customer characteristic data, and customer intent summary, to help users make better decisions on how to maintain customer relationships based on the lead records.

[0024] 6) In this application, the sign-out component corresponding to the lead record can be displayed in the second card component. After the sign-out component is triggered, the maintenance status information of the lead record is updated based on the consistency between the client's location and the customer's location. On the one hand, this helps users to efficiently maintain the status of the lead record, and on the other hand, it can effectively ensure the authenticity of the lead record maintenance.

[0025] 7) This application utilizes the deep semantic understanding capabilities of large language models to accurately identify customer intent, customer emotional tendencies, and the semantics of call content, thereby obtaining the customer's true potential needs and helping users make more accurate and efficient decisions and follow-ups regarding customer relationships.

[0026] 8) This application transforms unstructured data accumulated in calls into structured, quantifiable, and traceable structured features of target call records. On the one hand, it helps users quickly and accurately obtain customer relationship clues, and on the other hand, it accumulates data for maintaining customer relationships.

[0027] 9) This application obtains the quality of lead records based on customer intent and customer emotional inclination, and distinguishes between high-quality and low-quality lead records based on the quality of lead records. High-quality lead records are stored in the lead record database for easy maintenance and updates by users, while low-quality lead records are imported into the nurturing pool to avoid burdening users with low-quality lead records.

[0028] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a system architecture diagram applicable to the embodiments of this application.

[0031] Figure 2 A flowchart illustrating the information display method provided in this application embodiment.

[0032] Figure 3 This is a schematic diagram of an interface jump provided in an embodiment of this application.

[0033] Figure 4 This is a schematic diagram illustrating another interface transition provided in an embodiment of this application.

[0034] Figure 5 A flowchart of the clue record generation method provided in the embodiments of this application.

[0035] Figure 6 A schematic block diagram of an information display device provided in an embodiment of this application.

[0036] Figure 7 A schematic block diagram of a clue record generation device provided in an embodiment of this application.

[0037] Figure 8 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0038] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0039] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0040] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0041] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0042] Currently, when users (such as salespeople) manage customer relationships before a sale, they typically do so by manually recording customer information and determining whether the customer is a high-quality client requiring further follow-up. This method is inefficient for users, as they often miss identifying high-quality clients due to busy daily work schedules.

[0043] In view of this, this application provides a new approach. To facilitate understanding of this application, the system architecture on which this application is based will first be described. Figure 1 An exemplary system architecture that can be applied to embodiments of this application is shown, such as Figure 1 As shown, the system architecture may include: a CRM client and a server.

[0044] The server and client are the two main components of an application service. The server side uses a server as its primary hardware infrastructure and may include one or more software service modules. The server and client form a collaborative front-end and back-end.

[0045] The user terminal where the client resides can include, but is not limited to, smart mobile terminals, wearable devices, and PCs (Personal Computers). Smart mobile devices can include devices such as mobile phones, tablets, PDAs (Personal Digital Assistants), and connected car terminals. Wearable devices can include devices such as smartwatches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality) devices, and mixed reality devices (i.e., devices that support both virtual and augmented reality), etc.

[0046] CRM clients can be applications located on user terminals, or they can be functional units such as plugins or software development kits (SDKs) set up within applications.

[0047] A server can be a standalone server, a server cluster, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a hosting product within the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) services, such as high management difficulty and weak service scalability.

[0048] It should be understood that Figure 1 The server and client shown are merely illustrative. Depending on the implementation requirements, there can be any number of servers and clients.

[0049] Figure 2 This is a flowchart illustrating an information display method provided in an embodiment of this application. The method can be... Figure 1 The CRM client in the system shown is executed. For example... Figure 2 As shown, the method may include the following steps: Step 201: Display the first interface, which includes the call records of the user bound to the client. The call records are obtained after semantic analysis of the call content between the user and the client.

[0050] Step 202: In response to the operation of generating clue records for the target call record, a second interface is displayed, and the structured features of the target call record are displayed on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record.

[0051] Step 203: In response to triggering the operation of creating a lead record for the target call record, a lead record creation request is sent to the server to create the lead record. The lead record includes the structured features of the target call record, and the structured features of the target call record include customer feature data.

[0052] As can be seen from the above process, the method provided in this application can perform semantic analysis on call records obtained from the user's call content with the customer, perform structured analysis on the target call record in the call record to automatically display the structured features of the target call record to the user, and then respond to the operation of creating a lead record for the target call record to realize the automatic creation of the lead record. This method can automatically create the structured features of the target call record such as customer feature data. Compared with the manual recording method, both the level of intelligence and the efficiency of the user are effectively improved.

[0053] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments. It should be noted that the terms "first" and "second" involved in this disclosure do not have limitations in terms of size, order, or quantity, but are only used to distinguish them in name, such as "first interface" and "second interface" to distinguish different interfaces.

[0054] First, the above step 201, namely "displaying the first interface", will be described in detail with reference to the embodiments.

[0055] The first interface is mainly used to display the call records of users bound to the client. The call records are obtained after semantic analysis of the content of the calls between the user and the client.

[0056] In this embodiment, the display of the first interface can be triggered by the outbound call entry component on the third interface, which can be any service interface provided by the CRM system. As one possible implementation, the third interface can be the service homepage provided by the CRM system, which typically displays key sales data and frequently used function entry points. Since salespeople usually initiate calls to customers when maintaining customer relationships, i.e., outbound calls, the call records in this embodiment are typically outbound call records. Figure 3As shown in (a), one of the functional entry points can be an outbound call entry component. After the user triggers this outbound call entry component, the first interface is displayed. If there are currently no outbound call records, information such as "No outbound call records available" can be displayed. If there are already outbound call records, the generated outbound call records can be displayed on the first interface, such as... Figure 3 As shown in (b).

[0057] To develop new customers, users typically engage in voice calls, such as making phone calls. In this embodiment, the user can make phone calls to customers through a CRM system. Figure 3 The first interface shown in (b) can also display an outbound calling component. When a user triggers this component, a dialing interface is displayed, allowing the user to make calls to customers. In this approach, the server can obtain call records between users and customers through the CRM system's API interface, telephone exchange, or cloud call center. These call records can include metadata and call files. The metadata can include information such as the caller ID, called number, call start / end time, and call duration. The call file can be either voice content or text content obtained after recognizing the voice content.

[0058] After obtaining the call content, the server can perform semantic analysis on the call content to obtain the call record. For details on the specific analysis method, please refer to the subsequent detailed description of the method implementation embodiment executed by the server. The call record may include information such as customer intent, customer sentiment, summary information of the call content, customer category and the subject matter involved (e.g., a certain product, service, etc.), call time, duration, and the text content of the call.

[0059] In this embodiment of the application, the first interface may include at least one first card component, and each first card component corresponds to a call record (shown as an outbound call record in the figure). Figure 3 The first interface shown in (b) includes three first card components corresponding to call records. Each card component may include information such as call duration, call time, outbound name, and summary information, and may also include tag information, which includes at least one of customer intent tags, customer sentiment tags, customer category tags, and related target tags. For example Figure 3 In (b), “stronger intention” is a customer sentiment label, “supermarket” is a customer category label, and “Product A” is a label for the target involved.

[0060] In response to triggering one of the first card components, a details interface of the call record corresponding to the triggered first card component is displayed. The details interface includes at least one of the call record's call time, duration, content text, summary information, and tag information; wherein the tag information includes at least one of customer intent tag, customer sentiment tag, customer category tag, and target tag.

[0061] For example, click Figure 3 One of the first card components shown in (b) demonstrates Figure 3 The details page shown in (c) displays call time, duration, tag information, etc., and also has two tabs: when the "AI Summary" tab is selected, it displays a summary of the outbound call record; when the "Call Text" tab is selected, it displays the text of the outbound call record.

[0062] The following describes in detail step 202, namely, "in response to triggering the operation of generating clue records for the target call record, displaying the second interface, and displaying the structured features of the target call record on the second interface," with reference to the embodiments.

[0063] In this embodiment, at least one of the first interface and the details interface can display a clue record generation component; in response to triggering the clue record generation component, a second interface is displayed. Alternatively, the operation of generating clue records for a target call record can be triggered in other ways, such as through voice commands, special gestures, etc.

[0064] like Figure 3 As shown in (b) and (c), the lead generation component, i.e., the "Generate Lead" button in the figure, can be displayed on both the first interface and the details interface. When a user triggers the "Generate Lead" button corresponding to a certain outbound call record (the triggered outbound call record is called the target call record), the user will be redirected to the display shown in Figure (b). Figure 4 The second interface shown in (a) is shown in the middle.

[0065] The second interface displays the structured features of the target call record, which are obtained through structured analysis of the target call record. For details on how this structured analysis is performed, please refer to the subsequent examples of the methods executed on the server side.

[0066] In this embodiment, the structured features of the target call record may include customer characteristic data, and may further include customer intent summaries, the category to which the lead record belongs, etc. The customer characteristic data may include customer attribute data and demand data. Customer attribute data may include information such as the customer's name, region, address, and contact information, while demand information may include information such as interested products, budget range, pain points, competitors, and decision-making time. Figure 4 As shown in (a), after obtaining the structured features of the target call record from the server, it is automatically displayed on the second interface.

[0067] One possible approach is to display the structured features of the target call log on a second interface using editable components; such as... Figure 4 As shown in (a), the editable component may include a text input component, an option component, etc. Users can use the editable component to edit the structured features of the target call record on the second interface, such as modifying, deleting, or adding. The client responds to the editing of the structured features of the target call record through the editable component and displays the edited structured features of the target call record.

[0068] Additionally, since it takes time for the server to generate the structured features of the target call record and send them to the client, when the second interface is displayed in response to the operation of generating clue records for the target call record, if the structured features of the target call record have not yet been received, the structured features of the target call record displayed by each editable component on the second interface can be empty. A prompt message is displayed on the second interface to indicate that the structured features of the target call record are being generated, such as "AI intelligent filling in...".

[0069] The following describes step 203, namely, "in response to triggering the operation of creating a lead record for the target call record, sending a lead record creation request to the server to create a lead record", in detail with reference to the embodiments.

[0070] As one possible approach, the second interface also displays a clue record creation component, for example... Figure 4 The "Add" component shown in (a) responds to triggering the lead record creation component on the second interface, sending a lead record creation request to the server using the structured features of the target call record currently displayed on the second interface. Specifically, the structured features of the target call record currently displayed on the second interface (or the edited target call record's structured features if edited) are included in the lead record creation request and sent to the server, which then creates the lead record. The created lead record includes the aforementioned structured features of the target call record.

[0071] Furthermore, once the clue record is created, in response to the triggering of the operation to view the clue record, a fourth interface can be displayed, and at least one second card component can be displayed on the fourth interface. Each second card component corresponds to a clue record obtained from the server.

[0072] One possible approach is to send a lead record creation request to the server and then display the first screen. If a successful lead record creation response is received, the client can display a notification message indicating successful lead record creation on the first screen. Figure 4 As shown in (b), the notification message can be displayed as a pop-up window, and this pop-up window can also include a component that triggers the viewing of clue records, such as the "Go to View" button in the figure. After the user clicks this button, they will be redirected to a page like... Figure 4 The fourth interface shown in (c).

[0073] As another feasible approach, salespeople can also trigger a fourth interface by accessing the lead record view entry component on the CRM homepage. For example, clicking the task center entry component on the CRM homepage triggers the display of a task page, which contains multiple tabs such as a task list tab, a lead record list tab, and a visit record tab. If the salesperson clicks the lead record list tab, the fourth interface will be displayed.

[0074] The second card component displayed on the fourth interface corresponds to a lead record. This second card component can display information such as the lead record name, customer name, generation time, customer address, industry tags, etc. Figure 4 As shown in (c), a fourth interface of a second card component corresponding to a lead record is displayed. In response to triggering one of the second card components, a details interface for the lead record corresponding to the triggered second card component is displayed. This details interface may include at least one of the following: lead record quality information, maintenance status information, customer characteristic data, and customer intent summary. The lead record quality information can be obtained from the server side, which can utilize a large language model based on customer intent and customer sentiment tendencies in the corresponding call record. The maintenance status information represents the user's maintenance status of the lead record and may include information such as pending visit or visited.

[0075] Furthermore, the second card component also displays a sign-out component corresponding to the lead record. For example, after a user completes a visit to the customer corresponding to that lead record, they can click the sign-out component to update the maintenance status information of that lead record. In response to the action of triggering the sign-out component, if the client's location matches the customer location in the customer feature data contained in the lead record corresponding to the triggered sign-out component, then the maintenance status information of the lead record corresponding to the triggered sign-out component is updated, for example, updated to "visited".

[0076] Users can Figure 4 In the fourth interface shown in (c), clicking the “Visit Records” tab will display a list of visited lead records.

[0077] Figure 5 This is a flowchart of a clue record generation method provided in an embodiment of this application. The method can be... Figure 1 The CRM server in the system shown is executed. Figure 5 As shown, the method may include the following steps: Step 501: Obtain the content of the call between the user and the customer.

[0078] Step 502: Perform semantic analysis on the call content to obtain the user's call records.

[0079] Step 503: Perform structured analysis on the target call records in the call logs to obtain the structured features of the target call records.

[0080] Step 504: In response to the user's request to create a lead record for the target call record, create and store the lead record, which includes the structured features of the target call record, including customer feature data.

[0081] As can be seen from the above process, the method provided in this application can perform semantic analysis on the call records obtained from the user's call content with the customer, perform structured analysis on the target call records in the call records to automatically generate the structured features of the target call records, and then respond to the user's request to create a lead record for the target call records, create and store the lead record. This method can automatically create structured features of the target call records such as customer feature data. Compared with the manual recording method, both the level of intelligence and the user's efficiency are effectively improved.

[0082] First, the above step 501, namely "obtaining the call content between the user and the customer", will be described in detail with reference to the embodiments.

[0083] To develop new clients, users (such as salespeople) typically engage in voice calls with them, such as making phone calls. In this embodiment, users can make phone calls to clients through a CRM system.

[0084] In this approach, the server can obtain user-customer call records through CRM system APIs, telephone exchanges, or cloud call centers. These call records can include metadata and call files. Metadata can include information such as the caller ID, called number, call start / end time, and call duration. The call file can be either the voice message or a text file obtained by recognizing the voice message.

[0085] After obtaining the call content, the call logs are preprocessed. For example, if the call log is too short, it can be considered that the valid information in the log is insufficient, and the log is filtered out. If the call log shows that the call was not connected, it is deleted. Other preprocessing steps include removing filler words and noise from the call logs. Furthermore, if the call logs consist of text files, the text can be segmented and punctuation corrected to better conform to natural language standards.

[0086] The following describes step 502, namely "performing semantic analysis on the call content to obtain the user's call records," in detail with reference to an embodiment.

[0087] When performing semantic analysis on call records, a large model can be invoked to identify customer intent based on the call content, analyze customer sentiment, and perform semantic analysis. Then, based on the results of the semantic analysis, summary information of the call content, customer category, and the target involved can be obtained. The call record may include at least one of the following: call time, duration, content text of the call, summary information, and tag information. The tag information may include at least one of the following: customer intent tag, customer sentiment tag, customer category tag, and target involved tag.

[0088] As one possible approach, if the call log is in text format, prompts can be built using the call content to prompt large language models to identify customer intent, analyze customer sentiment, and perform semantic analysis based on the call content in the call log.

[0089] As another feasible approach, if the call record is in the form of voice, the voice record can be subjected to speech recognition to obtain the text content. Then, the text content can be used to construct prompts, prompting the large language model to identify customer intent, analyze customer sentiment, and perform semantic analysis based on the call content in the call record.

[0090] As another possible approach, if the call record is in the form of voice, prompts can be built using the voice content to prompt multimodal large models that identify customer intent, analyze customer sentiment, and perform semantic analysis based on the voice content.

[0091] The customer intent identified based on the call content can be of various types, such as whether they have a clear intention to buy, a trial request, or a product inquiry.

[0092] The customer sentiment profile obtained from the analysis can be such as positive, interested, neutral, negative, or resistant, or it can be more coarse-grained or more fine-grained sentiment profiles.

[0093] When performing semantic analysis, it is possible to identify and extract summary information of the call content, customer categories, and the subject matter involved (such as the goods or services involved).

[0094] Furthermore, after obtaining customer intent and sentiment, the client can determine the quality of the lead records corresponding to the target call record based on these parameters. One feasible approach is to use preset rules to quantitatively score (e.g., 1 to 10 points, or 1 to 100 points) or classify (e.g., high intent, medium intent, low intent, invalid) the lead records based on the customer intent and sentiment of the target call record. The clearer the customer intent, the higher the lead record quality; the more positive the customer sentiment, the higher the lead record quality. In addition, lead record quality can also be judged in conjunction with other factors, such as customer needs, the matching degree between the industry and the target offered by the user, etc.

[0095] The following describes in detail step 503, namely "performing a structured analysis of the target call record in the call log to obtain the structured features of the target call record", with reference to the embodiments.

[0096] In this step, entities and events of a preset type can be extracted from the target call record to obtain the structured features of the target call record. The structured features of the target call record may include customer feature data, and may further include customer intent summaries.

[0097] Customer characteristic data includes customer attribute data and demand data. Customer attribute data may include information such as customer name, region, address, and contact information, while demand information may include information such as products of interest, budget range, pain points, competitors, and decision-making time.

[0098] A summary of intent could be something like, “The customer highly approves of the performance of your product A and has clearly stated that the current contract will expire at the end of next month and there is an urgent need to replace it.”

[0099] The structured features of the target call record can be sent to the client in response to a client's request (e.g., the client requests the structured features of the target call record from the server in response to triggering the lead record generation component), so that the client can display them on the second interface.

[0100] The following describes step 504, namely "in response to a user's request to create a lead record for a target call record, create and store a lead record", in detail with reference to an embodiment.

[0101] In this embodiment of the application, all created clue records can be stored in the clue record database, or the storage of clue records in the clue record database can be determined based on the quality of the clue records.

[0102] As one possible approach, if the quality of the requested lead record meets preset quality requirements, then the lead record is created and stored in the lead record database. For example, if the lead record quality score is greater than or equal to a preset score threshold, or if the lead record quality level is greater than or equal to a preset level threshold, then the lead record can be stored in the lead record database for users to query and display.

[0103] If the quality of the requested lead record does not meet the preset quality requirements, the structured features of the target call record will be imported into the nurturing pool. Lead records in the nurturing pool can be used for subsequent marketing campaigns, or simply recorded without triggering sales follow-ups.

[0104] The lead record may include structured features of the target call record. These structured features may include customer characteristic data, and may also include at least one of the following: lead record quality information, maintenance status information, and customer intent summary. The maintenance status information represents the user's maintenance status of the lead record and may include terms such as "pending visit" or "visited."

[0105] Furthermore, already generated lead records can be assigned to users based on preset strategies. One possible approach is to assign lead records to the user from whom they originated; for example, the lead record could be assigned to the user whose call log it was based on.

[0106] As another feasible approach, a load balancing strategy can be used to distribute the created lead records to various users based on the customer characteristic data included in the lead records. For example, based on information such as the customer's industry and region, candidate users matching the customer's industry and region can be identified, and then a load balancing strategy can be used to distribute the created lead records to one or more of these candidate users.

[0107] Regardless of the allocation strategy used, once the assigned user is determined, the information of the created lead record can be sent to the assigned user's client or instant messaging account based on the allocation result. For example, sending the lead record to the assigned user's client allows the user to view the allocated lead record through their client. Alternatively, sending a link to the lead record to the user's instant messaging account allows the user to view the specific lead record details through the link.

[0108] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0109] Figure 6 This is a schematic block diagram of an information display device provided in an embodiment of this application. The device is disposed in... Figure 1 The CRM client in the illustrated architecture. For example... Figure 6 As shown, the device 600 includes: an interface display unit 601, an operation monitoring unit 602, and a request sending unit 603. The main functions of each component are as follows: The interface display unit 601 is configured to display a first interface, which includes the call records of the user bound to the client. The call records are obtained after semantic analysis of the call content between the user and the client.

[0110] Operation monitoring unit 602 is configured to monitor operations on the interface.

[0111] The interface display unit 601 is also configured to respond to the operation listening unit 602 listening to the operation that triggers the generation of clue records for the target call record, display a second interface, and display the structured features of the target call record on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record.

[0112] The request sending unit 603 is configured to send a lead record creation request to the server in response to the operation listening unit 602 detecting an operation that triggers the creation of a lead record for a target call record. The lead record includes the structured features of the target call record, which include customer feature data.

[0113] As one possible implementation, the interface display unit 601 is also configured to display a third interface before displaying the first interface. The third interface includes an outbound call entry component. In response to the operation monitoring unit 602 detecting the operation that triggers the outbound call entry component, the first interface is displayed. The first interface also includes an outbound call component, which is used to trigger a voice call between the user and the customer.

[0114] As one possible implementation, the first interface includes at least one first card component, each first card component corresponding to a call record; the interface display unit 601 can be further configured to: in response to the operation monitoring unit 602 detecting an operation that triggers one of the first card components, display a details interface of the call record corresponding to the triggered first card component, the details interface including at least one of the call time, duration, content text, summary information and tag information of the call record; wherein the tag information includes at least one of customer intent tag, customer sentiment tag, customer category tag and target tag involved.

[0115] As one possible implementation, at least one of the first interface and the details interface displays a clue record generation component; when the interface display unit 601 displays the second interface in response to the operation of triggering the generation of clue records for the target call record, it can be specifically configured to display the second interface in response to the operation listening unit 602 listening to the operation of triggering the clue record generation component.

[0116] As one possible implementation method, when the interface display unit 601 displays the structured features of the target call record on the second interface, it can be specifically configured to: display the structured features of the target call record on the second interface through an editable component; and in response to the operation monitoring unit 602 detecting the editing operation of the structured features of the target call record through the editable component, display the edited structured features of the target call record. Accordingly, the request sending unit 603 can be specifically configured to: in response to the operation listening unit 602 listening to the operation that triggers the clue record creation component on the second interface, send a clue record creation request to the server using the structured features of the target call record currently displayed on the second interface.

[0117] Furthermore, the interface display unit 601 can also be configured to: in response to the operation listening unit 602 detecting an operation that triggers the viewing of lead records, display a fourth interface and display at least one second card component on the fourth interface, each second card component corresponding to a lead record obtained from the server; in response to the operation listening unit 602 detecting an operation that triggers one of the second card components, display a details interface of the lead record corresponding to the triggered second card component, the details interface including at least one of lead record quality information, maintenance status information, customer characteristic data, and customer intention summary.

[0118] Furthermore, the second card component displays the sign-out component corresponding to the lead record; the interface display unit 601 can also be configured to: in response to the operation listening unit 602 listening to the operation that triggers the sign-out component, if the client's location is consistent with the customer location in the customer feature data contained in the lead record corresponding to the triggered sign-out component, then update the maintenance status information of the lead record corresponding to the triggered sign-out component.

[0119] Figure 7 This is a schematic block diagram of a clue record generation device provided in an embodiment of this application. The device is disposed in... Figure 1 The server-side of the CRM in the illustrated architecture. For example... Figure 7 As shown, the device 700 includes: a content acquisition unit 701, a content analysis unit 702, a request receiving unit 703, and a clue record creation unit 704, and may also include a clue record allocation unit 705. The main functions of each component are as follows: Content acquisition unit 701 is configured to acquire the content of a call between a user and a customer.

[0120] The content analysis unit 702 is configured to perform semantic analysis on the call content to obtain the user's call records; and to perform structured analysis on the target call records in the call records to obtain the structured features of the target call records.

[0121] The request receiving unit 703 is configured to receive a user's request to create a clue record for a target call record.

[0122] Lead record creation unit 704 is configured to create and store a lead record in response to a lead record creation request. The lead record includes structured features of the target call record, which includes customer feature data.

[0123] As one possible implementation method, when the content analysis unit 702 performs semantic analysis on the call content to obtain the user's call record, it can be specifically configured to: invoke a large language model, identify customer intent based on the call content, analyze customer sentiment, and perform semantic analysis; based on the results of the semantic analysis, obtain summary information of the call content, customer category, and the target involved; the call record includes at least one of the following: call time, duration, content text of the call, summary information, and tag information; the tag information includes at least one of the following: customer intent tag, customer sentiment tag, customer category tag, and target involved tag.

[0124] As one possible approach, when the content analysis unit 702 performs structured analysis on the target call record in the call log to obtain the structured features of the target call record, it can be specifically configured to: extract entities and events of a preset type from the target call record to obtain the structured features of the target call record, wherein the structured features of the target call record include customer feature data, or the structured features of the target call record include customer feature data and customer intention summary; wherein the customer feature data includes customer attribute data and demand data.

[0125] As one possible implementation method, the lead record creation unit 704 can be specifically configured to: if the quality of the requested lead record meets the preset quality requirements, then create the lead record and store it in the lead record database; if the quality of the requested lead record does not meet the preset quality requirements, then import the structured features of the target call record into the nurturing pool; wherein, the lead record quality is obtained based on the customer intent and customer emotional tendency of the target call record.

[0126] Furthermore, the lead record allocation unit 705 can be configured to: allocate the created lead records to each user using a load balancing strategy based on the customer characteristic data included in the lead records; and send the information of the created lead records to the client or instant messaging account of the allocated user based on the allocation result.

[0127] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The system and device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0128] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0129] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0130] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0131] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0132] in, Figure 8An exemplary architecture of an electronic device is shown, which may include a processor 810, a video display adapter 811, a disk drive 812, an input / output interface 813, a network interface 814, and a memory 820. The processor 810, video display adapter 811, disk drive 812, input / output interface 813, network interface 814, and memory 820 can communicate with each other via a communication bus 830.

[0133] The processor 810 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0134] The memory 820 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 820 can store the operating system 821 for controlling the operation of the electronic device 800, and the basic input / output system (BIOS) 822 for controlling the low-level operations of the electronic device 800. Additionally, it can store a web browser 823, a data storage management system 824, and an information display device 600 / clue recording generation device 700, etc. The aforementioned information display device 600 / clue recording generation device 700 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 820 and executed by the processor 810.

[0135] The input / output interface 813 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0136] Network interface 814 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0137] Bus 830 includes a pathway for transmitting information between various components of the device, such as processor 810, video display adapter 811, disk drive 812, input / output interface 813, network interface 814, and memory 820.

[0138] It should be noted that although the above-described device only shows the processor 810, video display adapter 811, disk drive 812, input / output interface 813, network interface 814, memory 820, bus 830, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0139] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0140] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An information display method, applied to the client side of a customer relationship management system, characterized in that, The method includes: The system displays a first interface, which includes call records of the user bound to the client. These call records are obtained by semantic analysis of the call content between the user and the client. In response to the operation of generating clue records for the target call record, a second interface is displayed, and the structured features of the target call record are displayed on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record. In response to triggering the operation of creating a lead record for the target call record, a lead record creation request is sent to the server to create the lead record. The lead record includes the structured features of the target call record, and the structured features of the target call record include customer feature data.

2. The method according to claim 1, characterized in that, Before displaying the first interface, it also includes: A third interface is displayed, which includes an outbound call entry component; In response to the operation of triggering the outbound call entry component, the first interface is displayed. The first interface also includes an outbound call component, which is used to trigger a voice call between the user and the customer.

3. The method according to claim 1, characterized in that, The first interface includes at least one first card component, and each first card component corresponds to a call record; In response to an operation that triggers one of the first card components, a details interface of the call record corresponding to the triggered first card component is displayed. The details interface includes at least one of the call record's call time, duration, content text, summary information, and tag information. The label information mentioned therein includes at least one of customer intent labels, customer sentiment labels, customer category labels, and labels related to the target.

4. The method according to claim 1, characterized in that, The step of displaying the structured features of the target call record on the second interface includes: displaying the structured features of the target call record on the second interface through an editable component; and displaying the edited structured features of the target call record in response to an editing operation on the structured features of the target call record through the editable component. The step of sending a lead record creation request to the server in response to triggering the operation of creating a lead record for the target call record includes: in response to triggering the operation of the lead record creation component on the second interface, sending a lead record creation request to the server using the structured features of the target call record currently displayed on the second interface.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to the operation of triggering the viewing of clue records, a fourth interface is displayed and at least one second card component is displayed on the fourth interface, each second card component corresponding to a clue record obtained from the server. In response to an operation that triggers one of the second card components, a details interface for the lead record corresponding to the triggered second card component is displayed. The details interface includes at least one of lead record quality information, maintenance status information, customer characteristic data, and customer intent summary.

6. The method according to claim 5, characterized in that, The second card component displays an exit component corresponding to the clue record; the method further includes: In response to the operation of triggering the sign-out component, if the location of the client is consistent with the customer location in the customer feature data contained in the lead record corresponding to the triggered sign-out component, then the maintenance status information of the lead record corresponding to the triggered sign-out component is updated.

7. A method for generating lead records, applied to the server side of a customer relationship management system, characterized in that, The method includes: Obtain the content of user and customer calls; Semantic analysis is performed on the call content to obtain the user's call records; The target call record in the call log is subjected to structured analysis to obtain the structured features of the target call record; In response to a lead record creation request for the target call record, a lead record is created and stored, the lead record including structured features of the target call record, the structured features of the target call record including customer feature data.

8. The method according to claim 7, characterized in that, The step of performing semantic analysis on the call content to obtain the user's call records includes: The large language model is invoked to identify customer intent, analyze customer sentiment, and perform semantic analysis based on the call content. Based on the results of the semantic analysis, a summary of the call content, customer category, and the target involved are obtained; The call log includes at least one of the following: call time, duration, text content of the call, summary information, and tag information; The tagging information includes at least one of customer intent tags, customer sentiment tags, customer category tags, and relevant target tags.

9. The method according to claim 7, characterized in that, The step of performing structured analysis on the target call record in the call log to obtain the structured features of the target call record includes: The target call record is subjected to entity and event extraction of a preset type to obtain the structured features of the target call record. The structured features of the target call record include customer feature data, or the structured features of the target call record include customer feature data and customer intention summary. The customer characteristic data mentioned above includes customer attribute data and demand data.

10. The method according to claim 8, characterized in that, The creation and storage of clue records includes: If the quality of the requested lead record meets the preset quality requirements, then the lead record is created and stored in the lead record database; If the quality of the requested lead record does not meet the preset quality requirements, the structured features of the target call record will be imported into the nurturing pool. The quality of the lead records is based on the customer intent and emotional inclination of the target call records.

11. An information display device, characterized in that, The device includes: The interface display unit is configured to display a first interface, which includes the call records of the user bound to the client. The call records are obtained by semantic analysis of the call content between the user and the client. The operation listening unit is configured to listen for operations on the interface. The interface display unit is further configured to respond to the operation monitoring unit detecting the operation that triggers the generation of clue records for the target call record, display a second interface, and display the structured features of the target call record on the second interface. The target call record is at least one of the user's call records, and the structured features of the target call record are obtained by performing structured analysis on the target call record. The request sending unit is configured to send a lead record creation request to the server to create a lead record in response to the operation listening unit detecting an operation that triggers the creation of a lead record for the target call record. The lead record includes the structured features of the target call record, and the structured features of the target call record include customer feature data.

12. A clue recording and generation device, characterized in that, The device includes: The content acquisition unit is configured to acquire the content of the user's call with the customer; The content analysis unit is configured to perform semantic analysis on the call content to obtain the user's call records; and to perform structured analysis on target call records in the call records to obtain the structured features of the target call records. The request receiving unit is configured to receive a clue record creation request for the target call record; A lead record creation unit is configured to create and store a lead record in response to the lead record creation request. The lead record includes structured features of the target call record, and the structured features of the target call record include customer feature data.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 10.

14. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 10.

15. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 10.

Images