Customer label extraction method and system based on AI large model, and medium

Abstract

The invention provides a customer tag extraction method based on an AI large model. The method comprises the following steps: pre-creating a portrait tag library; creating a visiting list, recording voice information in a customer reception process, and generating a sound recording file; converting the sound recording file into text information; extracting a portrait label matched with the customer in the text information based on large model analysis; and filling the portrait label matched with the customer into the visiting list. According to the client label extraction method based on the AI large model, the client key information can be rapidly and accurately extracted.

Description

Technical Field

[0001] The present invention relates to the field of real estate customer information extraction, and in particular to a customer label extraction method, system and medium based on an AI big model. Background Art

[0002] Currently, property consultants are unable to record customer information in a timely manner or quickly summarize useful labels for customers during reception. The reception time is too long and it is easy to forget key customer information.

[0003] As speech recognition and text-to-text technologies mature, and AI big models become prevalent, the customer reception process in the real estate industry must keep up with the times. However, the customer reception and enquiry process is still based on the old methods, which are time-consuming, laborious and prone to misremembering information. Therefore, a method that can automatically extract customer tags is needed. Summary of the invention

[0004] In response to the problems existing in the prior art, a customer label extraction method, system and medium based on AI big model are provided. The reception process is recorded through the work badge, and then the recording is converted into corresponding text content using the recording-to-text technology. Then, the big model technology is used to extract and summarize the text to obtain the label information required by the property consultant.

[0005] The first aspect of the present invention provides a customer tag extraction method based on an AI big model, comprising:

[0006] Pre-create a portrait tag library;

[0007] Create a visit form, record the voice information during the customer reception process, and generate a recording file;

[0008] Convert audio files into text messages;

[0009] Analyze and extract portrait tags that match customers from text information based on the big model and portrait tag library;

[0010] Fill in the customer-matching portrait label in the visit form.

[0011] As a preferred solution, the portrait label types in the portrait label library include text type, number type, time type, percentage type, single-choice type and multiple-choice type; wherein the single-choice type and the multiple-choice type are configured with specific options.

[0012] As a preferred solution, the converting of the recording file into text information specifically includes:

[0013] Extract the voice belonging to the customer from the recording file;

[0014] Convert the customer's voice into text messages.

[0015] As a preferred solution, extracting the voice belonging to the customer from the recording file specifically includes:

[0016] Analyze the recording file, remove the voice of the person who speaks the longest, and keep the voice as the customer's voice.

[0017] As a preferred solution, when converting the voice belonging to the customer into text information, the role to which the text segment belongs is marked in the converted text information.

[0018] As a preferred solution, the extraction of portrait tags matching customers from text information based on the large model and portrait tag library analysis specifically includes:

[0019] Input text information and established image labels into the pre-trained large model;

[0020] The large model matches the input text information with the portrait label and outputs multiple matching results, each of which includes a matching score.

[0021] The matching results with matching scores greater than the threshold are used as the portrait labels that match the customers.

[0022] As a preferred solution, after obtaining the portrait label that matches the customer, a secondary screening process is also included, including:

[0023] According to the image label type input to the large model, determine whether the image label output by the large model is the same. If so, retain the image label; if not, remove the image label.

[0024] As a preferred solution, the recording file is generated by the property consultant through the AI ​​work badge when receiving customers, and the recording file contains all voice information generated during the reception process.

[0025] The second aspect of the present invention proposes a customer label extraction system based on an AI big model, comprising a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the customer label extraction method based on the AI ​​big model as described in the first aspect.

[0026] The third aspect of the present invention proposes a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, are used to implement the process corresponding to the customer label extraction method based on the AI ​​large model described in the first aspect.

[0027] Compared with the prior art, the beneficial effects of adopting the above technical solution are:

[0028] 1. Save time. After the reception is completed, you can obtain key customer information

[0029] 2. Accurately extract configured customer portrait tags. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a flow chart of the customer label extraction method based on the AI ​​big model proposed in the present invention.

[0031] Figure 2 A system schematic diagram of an embodiment of the present application.

[0032] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0034] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0035] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0036] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0037] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In order to solve the problem that real estate consultants cannot record customer information in time during reception, cannot quickly summarize useful customer tags, and are prone to forgetting key customer information due to long reception time, the embodiment of the present invention proposes a customer tag extraction method based on AI big model, which analyzes voice text information based on AI big model and quickly extracts customer portrait tags. Please refer to Figure 1 , the specific plan is as follows:

[0039] Step 1: Create a portrait tag library in advance.

[0040] Before extracting customer portrait tags, the embodiment of the present invention proposes to pre-establish a portrait tag library as the basis for subsequent analysis. The portrait tag library contains the portrait tags and types that you want to extract. In this embodiment, the portrait tag types include text type, number type, time type, percentage type, single-choice type, and multiple-choice type, where the single-choice type and the multiple-choice type are configured with specific options. For example, the portrait tag name: customer budget, type: single-choice, option values: 1.5 million, 2 million, 3 million.

[0041] In actual applications, a portrait tag library can be created on the cloud platform and called during the analysis process, or it can be directly synchronized to the corresponding client system for storage after creation for subsequent use.

[0042] Step 2: Create a visit form, record the voice information during the customer reception process, and generate a recording file.

[0043] When receiving a customer, the property consultant first creates a visit form for the corresponding customer, and starts recording the ID card, recording the entire reception process. During the reception process, the property consultant asks the customer for information and learns about the customer. After the reception is completed, a recording file is generated for extracting information. Among them, the ID card that can be recorded can be implemented using existing products, which will not be described in detail here.

[0044] Step 3: Convert the recording file into text information.

[0045] The large model mainly extracts key information from text. In this embodiment, the recording file also needs to be converted into text information. However, the actual recording file contains not only the customer's voice information, but also the voice information of the property consultant. The voice of the property consultant is interference information when extracting customer information. Therefore, the voice of the property consultant in the recording file needs to be removed, only the customer's voice is retained, and the voice belonging to the customer is converted into text information.

[0046] Specifically, in this embodiment, the role described in the voice is determined by parsing the recording file and judging the speaking time of the character. The person with the longest total speaking time is the property consultant, and the corresponding voice is discarded. Furthermore, in actual applications, the property consultant will receive multiple customers at the same time. At this time, by parsing the recording file, the voice belonging to the customer is distinguished by role, and when converting the voice belonging to the customer into text information, the corresponding role is marked after each text.

[0047] Step 4: Extract the portrait labels that match the customers from the text information based on the big model analysis.

[0048] After obtaining the text information belonging to the customer, it is input into the big model together with the portrait tag selected from the portrait tag library. The big model extracts multiple matching results based on the information provided. In this embodiment, the matching score of the matching result is used to determine whether it meets the requirements, and only the matching result with a matching score greater than the threshold is used as the portrait tag matching the customer. In actual applications, the big model can be configured in different types according to the requirements, and multiple big models can be configured according to the requirements to perform analysis and extraction at the same time.

[0049] In order to avoid abnormal extraction of large model labels, a secondary screening process is also proposed in this embodiment, including: judging whether the portrait labels output by the large model are the same according to the portrait label type input to the large model, if so, retaining the portrait label; if not, discarding the portrait label. For example, if the portrait label is in digital format and the large model returns a non-digital format, the result will be filtered at this time, and other portrait labels are judged similarly. This operation ensures that the extracted portrait labels are portrait labels that meet the requirements, thereby improving the accuracy of the portrait labels.

[0050] By selecting different portrait labels and inputting them into the big model, all the required customer portrait labels can be obtained.

[0051] Step 5: Fill in the customer-matching portrait label in the visit form.

[0052] After obtaining the required customer portrait labels, fill them in the visit form and save them locally or in the cloud.

[0053] The customer label extraction method based on the AI ​​big model proposed in the present invention can quickly and accurately extract customer key information.

[0054] Please refer to Figure 2 The embodiment of the present invention also proposes a customer label extraction system based on an AI big model, including a memory 101 and a processor 102, wherein the memory 101 stores a computer program corresponding to the customer label extraction method based on the AI ​​big model as described above and which can be loaded and executed by the processor 102.

[0055] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the customer tag extraction system of an embodiment of the present application is shown.

[0056] It should be noted that Figure 3 The computer system 200 of the customer tag extraction system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0057] like Figure 3 As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 202 or the program loaded from the storage part 208 to the random access memory (RAM) 203, such as executing the method described in the above embodiment. In the RAM 203, various programs and data required for system operation are also stored. The CPU 201, ROM 202 and RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0058] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed so that a computer program read therefrom is installed into the storage section 208 as needed.

[0059] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 209, and / or installed from a removable medium 211. When the computer program is executed by a central processing unit (CPU) 201, various functions defined in the system of the present application are executed.

[0060] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0061] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0062] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0063] As another aspect, the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the customer label extraction method based on the AI ​​large model described in the above embodiment.

[0064] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the customer tag extraction method based on the AI ​​large model described in the above embodiment.

[0065] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0066] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0067] For those skilled in the art, the specific meanings of the above terms in the present invention can be understood in specific situations; the drawings in the embodiments are used to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0068] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A customer label extraction method based on AI big model, characterized in that: include: Pre-create a portrait tag library; Create a visit form, record the voice information during the customer reception process, and generate a recording file; Convert audio files into text messages; Analyze and extract portrait tags that match customers from text information based on the big model and portrait tag library; Fill in the customer-matching portrait label in the visit form.

2. The customer label extraction method based on AI big model according to claim 1 is characterized in that: The portrait label types in the portrait label library include text type, number type, time type, percentage type, single-choice type and multiple-choice type; among which, the single-choice type and the multiple-choice type are configured with specific options.

3. The customer label extraction method based on AI big model according to claim 1 is characterized in that: The step of converting the recording file into text information specifically includes: Extract the voice belonging to the customer from the recording file; Convert the customer's voice into text messages.

4. The customer label extraction method based on AI big model according to claim 3 is characterized in that: The extracting of the voice belonging to the customer in the recording file specifically includes: Analyze the recording file, remove the voice of the person who speaks the longest, and keep the voice as the customer's voice.

5. The customer label extraction method based on AI big model according to claim 3 or 4 is characterized in that: When converting the voice belonging to the customer into text information, the role to which the text segment belongs is marked in the converted text information.

6. The customer label extraction method based on AI big model according to claim 1 is characterized in that: The analysis and extraction of portrait tags matching the customer in the text information based on the big model and the portrait tag library specifically includes: Input text information and established image labels into the pre-trained large model; The large model matches the input text information with the portrait label and outputs multiple matching results, each of which includes a matching score. The matching results with matching scores greater than the threshold are used as the portrait labels that match the customers.

7. The customer label extraction method based on AI big model according to claim 1 is characterized in that: After obtaining the portrait label that matches the customer, a secondary screening process is also included, including: According to the image label type input to the large model, determine whether the image label output by the large model is the same. If so, retain the image label; if not, remove the image label.

8. The customer label extraction method based on AI big model according to claim 1 is characterized in that: The recording file is generated by the property consultant using the AI ​​ID card when receiving customers, and the recording file contains all voice information generated during the reception process.

9. A customer label extraction system based on AI big model, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the customer tag extraction method based on the AI ​​large model as described in any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by the processor, they are used to implement the process corresponding to the customer label extraction method based on the AI ​​big model described in any one of claims 1 to 8.

Images