House source introduction verbal skill acquisition method and device, electronic equipment and storage medium

Abstract

The invention provides a housing resource introduction verbal skill acquisition method and device, electronic equipment and a storage medium, and relates to the technical field of information processing. The method comprises the following steps: determining a target housing resource name; according to the target housing resource name and the corresponding relation between the housing resource name and the introduction verbal skill, at least one target introduction verbal skill corresponding to the target housing resource name is determined, and the corresponding relation between the housing resource name and the introduction verbal skill is obtained by performing information extraction on housing resource introduction information corresponding to excellent brokers; and according to the at least one target introduction verbal skill, determining a final introduction verbal skill corresponding to the target housing resource. According to the method, the high-quality house source introduction information is extracted to obtain the house source introduction verbal skill for the broker to use, so that the broker can be helped to explain the excellent house source introduction verbal skill for the house source consulted by the customer or the community, the service quality is improved, and more opportunities for watching are grasped.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method, device, electronic device and storage medium for acquiring property introduction speech. Background Art

[0002] A key step in recommending a property is describing it. Brokers are more familiar with properties in their area and can easily explain them. However, with the increasing number of clients viewing properties across different regions, brokers often rely on self-referrals from owners, reviews, and information input by property maintainers to describe unfamiliar properties.

[0003] However, the information on property introductions obtained through the above methods is scattered, making it difficult for brokers to grasp key features, resulting in missed viewing or sales opportunities. Summary of the Invention

[0004] The present invention provides a method, device, electronic device and storage medium for obtaining property introduction scripts, which are used to solve the defect in the prior art that the introduction information of cross-regional properties is scattered and it is difficult to grasp the key features. By extracting high-quality property introduction information, property introduction scripts are obtained for use by brokers, which can help brokers explain excellent property introduction scripts to the properties or communities inquired by customers, improve service quality, and seize more viewing opportunities.

[0005] The present invention provides a method for obtaining a property introduction script, comprising the following steps: Determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to; Determining at least one target introduction line corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction line, wherein the correspondence between the property name and the introduction line is obtained by extracting property introduction information corresponding to outstanding real estate agents; Based on the at least one target introduction line, a final introduction line corresponding to the target property is determined.

[0006] According to a method for obtaining real estate listing introduction scripts provided by the present invention, when a current broker is communicating with a target client, historical communication information corresponding to the target client is obtained, wherein the historical communication information includes communication information previously generated between the target client and at least one broker via at least one communication channel, and / or communication information currently generated between the target client and the current broker; The property information is extracted from the historical communication information to obtain the target property name.

[0007] According to a method for obtaining property introduction speech provided by the present invention, extracting property information from the historical communication information to obtain the target property name includes: Performing contextual semantic integration on the historical communication information to obtain integrated communication information; Extracting property information from the integrated communication information to obtain an initial property name; In a case where the initial property listing name includes at least two property listing names, screening the at least two property listing names to determine the target property listing name; In the case that the initial property name includes a property name, the initial property name is determined to be the target property name.

[0008] According to a method for obtaining a property introduction script provided by the present invention, before determining the target property name, the method further includes: Determining a target broker based on the broker viewing data and / or the broker sales data, wherein the target broker is a broker who meets the requirements of an excellent broker and is screened based on the broker viewing data and / or the broker sales data; Extracting information about the target property listing corresponding to the target broker to obtain a correspondence between the property listing name and the introduction words, wherein the target property listing information corresponding to the target broker is used to represent the target broker's introduction of the property listing; The correspondence between the house source name and the house site identity is determined based on the house site dictionary technology, and then the correspondence between the house site identity and the introduction language is obtained based on the correspondence between the house site identity and the introduction language.

[0009] According to a method for obtaining a property introduction script provided by the present invention, extracting target property introduction information corresponding to the target broker to obtain a correspondence between the property name and the introduction script includes: Extracting the target property introduction information to obtain the property name and the introduction words, wherein the property name includes the target community and the target property; Determining that the introduction speech includes the first information or the second information; If the introduction script includes first information, a correspondence between the target community and the introduction script is obtained, wherein the first information includes at least one of traffic information, geographical location, business district, building age, parking space, and surrounding facilities; If the introduction script includes second information, a corresponding relationship between the target property and the introduction script is obtained, and the second information includes at least one of area, floor, total price, decoration, and apartment type.

[0010] According to a method for obtaining a property listing introduction script provided by the present invention, before extracting the target property listing introduction information corresponding to the target broker to obtain the corresponding relationship between the property listing name and the introduction script, the method further includes: The target property introduction information corresponding to the target broker is obtained through a target communication channel, where the target communication channel includes at least one of an instant messaging tool, an enterprise chat tool, and an enterprise telephone call.

[0011] The present invention also provides a device for acquiring housing introduction speech, comprising the following modules: A property identification module is used to determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to; a script determination module, configured to determine at least one target introduction script corresponding to the target property name based on the target property name and a correspondence between the property name and the introduction script, wherein the correspondence between the property name and the introduction script is obtained by extracting property introduction information corresponding to outstanding agents; The result generation module is used to determine the final introduction words corresponding to the target property based on the at least one target introduction words.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for obtaining the property introduction script as described in any one of the above-mentioned methods is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for obtaining the property introduction script as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for obtaining the property introduction script as described in any of the above.

[0015] The method, device, electronic device and storage medium for obtaining property introduction scripts provided by the present invention extract information from high-quality property introduction information to obtain property introduction scripts for use by brokers. This can help brokers explain excellent property introduction scripts to the properties or communities inquired by customers, improve service quality, and seize more viewing opportunities. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow charts of the method for obtaining the property introduction script provided by the present invention.

[0018] Figure 2 It is a flowchart of the method for determining the target property name provided by the present invention.

[0019] Figure 3 This is the second flow chart of the method for obtaining the property introduction script provided by the present invention.

[0020] Figure 4 It is a schematic diagram of the architecture of the system for obtaining house introductions provided by the present invention.

[0021] Figure 5 It is a structural diagram of the device for obtaining the housing introduction words provided by the present invention.

[0022] Figure 6 It is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0024] A key step in recommending a property is describing it. Brokers are more familiar with properties in their area and can easily explain them. However, with the increasing number of clients viewing properties across different regions, brokers often rely on self-referrals from owners, reviews, and information input by property maintainers to describe unfamiliar properties.

[0025] However, the information on property introductions obtained through the above methods is scattered, making it difficult for brokers to grasp key features, resulting in missed viewing or sales opportunities.

[0026] In view of this, an embodiment of the present invention provides a method for obtaining property introduction scripts, comprising determining a target property name; determining at least one target introduction script corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction script, wherein the correspondence between the property name and the introduction script is obtained by extracting property introduction information corresponding to excellent real estate agents; and determining a final introduction script corresponding to the target property based on the at least one target introduction script. This method extracts property introduction scripts from high-quality property introduction information for use by real estate agents, and can help real estate agents provide excellent property introduction scripts for properties or communities inquired about by clients, thereby improving service quality and seizing more viewing opportunities.

[0027] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0028] Figure 1 This is one of the flow charts of the method for obtaining the house introduction script provided by the present invention. The method for obtaining the house introduction script can be applied to electronic devices, which can be various types of devices with information processing capabilities during implementation. For example, the electronic device can include a personal computer, a laptop, a PDA or a server, etc.; the electronic device can also be a mobile terminal, for example, the mobile terminal can include a mobile phone, a car computer, a tablet computer or a projector, etc. Figure 1 As shown, the method may include the following steps 101 to 103: Step 101: Determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to.

[0029] It should be noted that the target property name is the name of the property or community that the target customer has recently paid attention to. There are many ways to determine the target property name, for example, it can be determined by the property name told by the user, or it can be determined based on the property name input by the user, etc. The present invention does not limit the method of determining the target property name.

[0030] Step 102: Determine at least one target introduction line corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction line. The correspondence between the property name and the introduction line is obtained by extracting the property introduction information corresponding to the excellent broker.

[0031] It should be noted that the system stores the correspondence between property listing names and introductory lines. After determining the target property listing name, the system can determine at least one target introductory line corresponding to the target property listing name based on the correspondence between the property listing name and the introductory lines. The correspondence between property listing names and introductory lines can also be stored in a property listing line library, which can store the correspondence between property listing names and property listing line library for brokers to query.

[0032] The correspondence between property listing names and introductory language can be obtained by extracting information from excellent real estate agents' property listing introductions. There are many ways to extract information from excellent real estate agents' property listing introductions, such as using natural language models or artificial intelligence (AI). The present invention does not limit the method for obtaining the correspondence between property listing names and introductory language.

[0033] For example, an excellent broker may be a top-seller among brokers. The present invention may use the real estate dictionary capability to map the property name and the real estate identity ID, and then obtain x recently analyzed top-seller scripts based on the real estate ID.

[0034] Step 103: Determine the final introduction script corresponding to the target property based on the at least one target introduction script.

[0035] It should be noted that there are many methods for determining the final introduction words corresponding to the target property based on the at least one target introduction words, such as AI analysis or model analysis. The present invention does not limit the method for determining the final introduction words corresponding to the target property based on the at least one target introduction words.

[0036] For example, after obtaining x top-selling scripts, a secondary AI analysis can be performed on the x top-selling scripts to generate and record the script for introducing this property.

[0037] It can be understood that the method for obtaining property introduction scripts provided by the present invention obtains the correspondence between property name and introduction scripts by extracting information from property introduction information corresponding to excellent brokers. After determining the target property name, at least one target introduction script corresponding to the target property name is determined based on the target property name and the correspondence between the property name and the introduction scripts. The method then obtains the final introduction script based on the at least one target introduction script. This method can summarize the information on property introductions by excellent brokers and provide it to the current broker, so that the current broker can explain the excellent introduction scripts and key features of the property or community that the customer has inquired about, thereby improving service quality and seizing more viewing opportunities.

[0038] In some embodiments, the target property name may be determined by determining the neighborhood or property that the client is currently interested in based on communication information between the client and the broker.

[0039] Figure 2 This is a flow chart of the method for determining the target property name provided by the present invention. Figure 2 As shown, determining the target property name may include: Step 201: When the current broker is communicating with the target customer, historical communication information corresponding to the target customer is obtained, where the historical communication information includes communication information previously generated between the target customer and at least one broker through at least one communication channel, and / or communication information currently generated between the target customer and the current broker.

[0040] It should be noted that if the target customer is communicating with a broker for the first time, the target customer's communication information with the current broker is obtained. If the target customer has communicated with multiple brokers, the target customer's previous communication information with at least one broker through at least one communication channel is obtained, as well as the target customer's current communication information with the current broker. Alternatively, only the target customer's previous communication information with at least one broker through at least one communication channel is obtained. The scope of historical communication information can be set as needed.

[0041] Among them, the channels for target customers to communicate with brokers may include instant messaging (IM), corporate WeChat, 400 calls and other channels.

[0042] Step 202: extracting property information from the historical communication information to obtain the target property name.

[0043] It should be noted that there are many ways to extract property information from the historical communication information and obtain the target property name, such as through AI extraction or large-model natural language processing. The present invention does not limit the method for extracting property information from the historical communication information and obtaining the target property name.

[0044] For example, when a broker serves a client, he or she can aggregate chat information from multiple channels in real time, and AI can extract the names of properties / communities that the client is most interested in.

[0045] Furthermore, the extracting of property information from the historical communication information to obtain the target property name may include: performing contextual semantic integration on the historical communication information to obtain integrated communication information; extracting property information from the integrated communication information to obtain an initial property name; when the initial property name includes at least two property names, screening the at least two property names to determine the target property name; when the initial property name includes one property name, determining the initial property name to be the target property name.

[0046] It should be noted that the contextual semantic integration of the historical communication information can be performed using a contextual semantic integration model. The contextual semantic integration model can be implemented using a semantic understanding model or a deep learning model (such as BERT, GPT, etc.). These models can deeply understand the semantic relationships in the text, capture key information in the context, and effectively integrate it. The present invention does not limit the method for contextual semantic integration of the historical communication information.

[0047] The method of extracting property information from the integrated communication information and obtaining the initial property name can be to use a named entity recognition (NER) model or a relationship extraction model. Named entity recognition (NER): The NER model can recognize specific entities in the text, such as names of people, places, and institutions. In property information extraction, the NER model can be trained to recognize key information such as property names, addresses, and prices. The relationship extraction model goes a step further and can not only recognize entities, but also recognize the relationships between entities. In property information extraction, the relationship extraction model can be used to identify the relationship between a property and its attributes (such as price, area, year of construction, etc.). By training the model, it can learn these relationship features and automatically extract them from new text. The present invention does not limit the method of extracting property information from the integrated communication information.

[0048] In the case that the initial property name includes at least two property names, the at least two property names are screened, and a method for determining the target property name can adopt a screening model based on user needs, a screening model based on property features, a recommendation model based on machine learning, or an iterative model based on user feedback, etc. The present invention does not limit the method for screening the at least two property names.

[0049] In some embodiments, before obtaining the property introduction script, it is necessary to obtain the correspondence between the property name and the introduction script, that is, to generate a property script library.

[0050] Figure 3 This is the second flow chart of the method for obtaining the house introduction words provided by the present invention. Figure 3As shown, the method for obtaining the housing listing introduction script may include: Step 301: Determine a target broker based on broker viewing data and / or broker sales data. The target broker is a broker who meets the requirements of an excellent broker and is screened based on the broker viewing data and / or broker sales data.

[0051] It should be noted that the foundation for establishing a library of real estate listing scripts is to identify outstanding real estate agents. Outstanding real estate agents can be identified based on their showings and / or sales data. For example, the top five real estate agents ranked by showings last week could be identified as outstanding real estate agents, or the top five real estate agents ranked by sales last week could also be identified as outstanding real estate agents. The present invention does not limit the screening conditions or methods, and these can be set based on needs or actual circumstances.

[0052] For example, target brokers can be determined by processing data on top-selling brokers and clients. Target brokers are those with viewings and sales data from the past 30 days. Top-selling brokers can be selected by inputting all viewings and sales broker and client data into a model or algorithm, with the output being brokers with either of two types of data (viewings or sales) from the past 30 days.

[0053] Step 302: extract the target property introduction information corresponding to the target broker to obtain the corresponding relationship between the property name and the introduction words. The target property introduction information corresponding to the target broker is used to represent the information of the target broker's introduction of the property.

[0054] It should be noted that after determining the target broker, the target property introduction information corresponding to the target broker is obtained, and information extraction is performed on the target property introduction information to obtain the corresponding relationship between the property name and the introduction language. The information extraction method can be extracted using AI technology or large-scale natural language processing. The present invention does not limit the method of extracting the target property introduction information corresponding to the target broker to obtain the corresponding relationship between the property name and the introduction language.

[0055] For example, AI can be used to refine and analyze the property name and description.

[0056] Step 303: Determine the correspondence between the property name and the property identity identifier based on the property dictionary technology, and then obtain the correspondence between the property name and the introduction language based on the correspondence between the property identity identifier and the introduction language.

[0057] It should be noted that the present invention can use the real estate dictionary capability to map the house name and the real estate ID to form a relationship library of real estate ID-speech introduction.

[0058] Exemplarily, the present invention may first use a building dictionary to obtain a building ID according to the name, and then store it in a Mysql database: building name - building ID - wording introduction.

[0059] Step 304: Determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to.

[0060] The description of step 304 may refer to the description of step 101 in the aforementioned embodiment.

[0061] Step 305: Determine at least one target introduction line corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction line. The correspondence between the property name and the introduction line is obtained by extracting the property introduction information corresponding to the excellent broker.

[0062] The description of step 305 may refer to the description of step 102 in the aforementioned embodiment.

[0063] Step 306: Determine the final introduction script corresponding to the target property based on the at least one target introduction script.

[0064] The description of step 306 may refer to the description of step 103 in the aforementioned embodiment.

[0065] Furthermore, the information extraction of the target property introduction information corresponding to the target broker to obtain the correspondence between the property name and the introduction language may include: information extraction of the target property introduction information to obtain the property name and the introduction language, wherein the property name includes the target community and the target property; determining whether the introduction language contains the first information or the second information; if the introduction language includes the first information, the correspondence between the target community and the introduction language is obtained, and the first information includes at least one of traffic information, geographical location, business district, building age, parking space, and surrounding facilities; if the introduction language includes the second information, the correspondence between the target property and the introduction language is obtained, and the second information includes at least one of area, floor, total price, decoration, and apartment type.

[0066] It should be noted that there are many ways to extract information from the target property listing information to obtain the property name and introductory text. For example, one can first integrate the target property listing information with contextual sentences, then extract information from the integrated information to obtain the property name and introductory text. Contextual semantic integration can be performed using a contextual semantic integration model. This can be implemented using a semantic understanding model or a deep learning model (such as BERT or GPT). These models can deeply understand semantic relationships within text, capture key contextual information, and effectively integrate it. The present invention does not limit the method for performing contextual semantic integration on the historical communication information. Property information can be extracted from the integrated information to obtain the property name and introductory text using a named entity recognition (NER) model or a relation extraction model. Named entity recognition (NER): NER models can identify specific entities in text, such as names of people, places, and organizations. In property information extraction, NER models can be trained to recognize key information such as property name, address, and price. Relationship extraction models go a step further, identifying not only entities but also the relationships between them. In property information extraction, relationship extraction models can be used to identify the relationships between properties and their attributes (such as price, area, and year of construction). By training the model, it learns these relationship features and automatically extracts them from new text. Therefore, the present invention does not limit the method for extracting information from the target property description to obtain the property name and description.

[0067] Among them, after obtaining the name of the property and the introduction script, it can be determined whether the introduction script contains the first information or the second information; if the introduction script includes the first information, the correspondence between the target community and the introduction script is obtained, and the first information includes at least one of traffic information, geographical location, business district, building age, parking space, and surrounding facilities; if the introduction script includes the second information, the correspondence between the target property and the introduction script is obtained, and the second information includes at least one of area, floor, total price, decoration, and apartment type.

[0068] It is understandable that if the introduction includes traffic information, geographical location, business district, building age, parking spaces, surrounding facilities, etc., it can be considered that the introduction is for a certain community. If the introduction includes area, floor, total price, decoration, apartment type, etc., it can be considered that the introduction is for a certain house. This method can more accurately establish the correspondence between the house source and the introduction.

[0069] Furthermore, before extracting the target property introduction information corresponding to the target broker and obtaining the correspondence between the property name and the introduction words, the method may also include: obtaining the target property introduction information corresponding to the target broker through a target communication channel, and the target communication channel includes at least one of an instant messaging tool, a corporate chat tool, and a corporate telephone call.

[0070] It should be noted that the present invention can aggregate chat data between target brokers and clients through multiple channels, such as IM, 400 calls, and WeChat. The more channels used, the more comprehensive the data obtained. Using multiple channels to obtain target property introduction information corresponding to the target broker can extract more accurate property names and introduction language.

[0071] This invention leverages AI technology to analyze and extract top-selling listing descriptions from channels like instant messaging (IM), WeChat for Business, and 400 calls, building a library of optimized listing descriptions. When customers inquire about a property, the system recommends optimal descriptions based on the listing's title in real time, helping agents provide more professional and personalized service. This allows agents to leverage not only basic listing information but also the library of descriptions to improve service quality and secure more viewing opportunities.

[0072] The following describes an exemplary application of an embodiment of the present invention in a practical application scenario.

[0073] Figure 4 This is a schematic diagram of the architecture of the system for obtaining house introductions provided by the present invention. Figure 4 As shown, excellent real estate agents' explanations of the H community have formed a library of words for introducing housing listings, which can accurately serve other real estate agents in introducing housing listings in the H community.

[0074] Based on the foregoing embodiments, an embodiment of the present invention provides a device for acquiring property introduction speech. The modules included in the device and the units included in each module can be implemented by a processor; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0075] The following describes the device for obtaining the house introduction words provided by the present invention. The device for obtaining the house introduction words described below and the method for obtaining the house introduction words described above can refer to each other.

[0076] Figure 5 This is a schematic diagram of the structure of the device for obtaining the house introduction words provided by the present invention. Figure 5As shown, the apparatus 700 includes a housing source determination module 701, a speech technique determination module 702, and a result generation module 703, wherein: The housing source determination module 701 is used to determine the target housing source name, where the target housing source name is the name of the housing source or community that the target customer has recently paid attention to; A script determination module 702 is configured to determine at least one target introduction script corresponding to the target property name based on the target property name and the corresponding relationship between the property name and the introduction script, wherein the corresponding relationship between the property name and the introduction script is obtained by extracting property introduction information corresponding to excellent real estate agents; The result generation module 703 is used to determine the final introduction words corresponding to the target property according to the at least one target introduction words.

[0077] In some embodiments, the housing source determination module 701 includes an information acquisition unit and a housing source extraction unit, wherein: The information acquisition unit is configured to acquire historical communication information corresponding to the target client when the current broker communicates with the target client, the historical communication information including communication information previously generated between the target client and at least one broker via at least one communication channel, and / or communication information currently generated between the target client and the current broker; The housing resource extraction unit is configured to extract housing resource information from the historical communication information to obtain the target housing resource name.

[0078] In some embodiments, the property extraction unit is specifically used to: perform contextual semantic integration on the historical communication information to obtain integrated communication information; perform property information extraction on the integrated communication information to obtain an initial property name; when the initial property name includes at least two property names, screen the at least two property names to determine the target property name; when the initial property name includes one property name, determine the initial property name as the target property name.

[0079] In some embodiments, the device further includes a broker determination module, a speech extraction module, and a relationship establishment module, wherein: The broker determination module is used to determine a target broker based on the broker viewing data and / or the broker sales data, wherein the target broker is a broker who meets the requirements of an excellent broker and is screened based on the broker viewing data and / or the broker sales data; The target listing introduction information corresponding to the target broker is extracted by the target broker to obtain a correspondence between the listing name and the introduction words. The target listing introduction information corresponding to the target broker is used to represent the target broker's introduction of the listing; The relationship establishment module is used to determine the correspondence between the house name and the real estate identity identifier based on the real estate dictionary technology, and then obtain the correspondence between the house name and the introduction language based on the correspondence between the real estate identity identifier and the introduction language.

[0080] In some embodiments, the wording extraction module is specifically used to: extract information from the target housing introduction information to obtain the housing name and the introduction wording, where the housing name includes the target community and the target housing; determine whether the introduction wording contains the first information or the second information; if the introduction wording includes the first information, then obtain the corresponding relationship between the target community and the introduction wording, where the first information includes at least one of traffic information, geographical location, business district, building age, parking space, and surrounding facilities; if the introduction wording includes the second information, then obtain the corresponding relationship between the target housing and the introduction wording, where the second information includes at least one of area, floor, total price, decoration, and apartment type.

[0081] In some embodiments, the device also includes a speech acquisition module, which is used to obtain the target property introduction information corresponding to the target broker through a target communication channel, and the target communication channel includes at least one of an instant messaging tool, an enterprise chat tool, and an enterprise telephone call.

[0082] In an embodiment of the present invention, by extracting high-quality property introduction information to obtain property introduction scripts for use by brokers, brokers can be helped to explain excellent property introduction scripts to the properties or communities inquired by customers, improve service quality, and seize more viewing opportunities.

[0083] Figure 6 Schematic diagram of the physical structure of the electronic device provided by the present invention. Figure 6As shown, the electronic device may include: a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other via the communications bus 840. The processor 810 may call logic instructions in the memory 830 to execute a method for obtaining a property introduction script, the method comprising: determining a target property name, wherein the target property name is the name of a property or neighborhood that a target customer has recently shown interest in; determining at least one target introduction script corresponding to the target property name based on the target property name and a correspondence between the property name and the introduction script, wherein the correspondence between the property name and the introduction script is obtained by extracting property introduction information corresponding to excellent real estate agents; and determining a final introduction script corresponding to the target property based on the at least one target introduction script.

[0084] Furthermore, the logic instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0085] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for obtaining the property introduction script provided by the above methods, which method includes: determining the target property name, which is the name of the property or community that the target customer has recently paid attention to; determining at least one target introduction script corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction script, which is obtained by extracting information from the property introduction information corresponding to excellent brokers; and determining the final introduction script corresponding to the target property based on the at least one target introduction script.

[0086] The computer program product includes one or more computer instructions. When loaded and executed on a computer, the computer program instructions fully or partially perform the processes or functions described in accordance with the embodiments of the present invention. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium capable of computer storage or a data storage device such as a server or data center that integrates one or more available media. The available medium may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0087] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for obtaining property introduction scripts provided by the above-mentioned methods, the method comprising: determining the target property name, the target property name being the name of a property or community that the target customer has recently paid attention to; determining at least one target introduction script corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction script, the correspondence between the property name and the introduction script being obtained by extracting information from the property introduction information corresponding to an excellent broker; and determining the final introduction script corresponding to the target property based on the at least one target introduction script.

[0088] The computer-readable storage medium may be any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0089] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0090] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0091] Computer program code for performing the operations described herein may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0093] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for obtaining a property introduction script, characterized in that: include: Determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to; Determining at least one target introduction line corresponding to the target property name based on the target property name and the correspondence between the property name and the introduction line, wherein the correspondence between the property name and the introduction line is obtained by extracting property introduction information corresponding to outstanding real estate agents; Based on the at least one target introduction line, a final introduction line corresponding to the target property is determined.

2. The method for obtaining the property introduction script according to claim 1, characterized in that: Determining the target property name includes: When the current broker is communicating with the target client, obtaining historical communication information corresponding to the target client, the historical communication information including communication information previously generated between the target client and at least one broker via at least one communication channel, and / or communication information currently generated between the target client and the current broker; The property information is extracted from the historical communication information to obtain the target property name.

3. The method for obtaining the property introduction script according to claim 2, characterized in that: The extracting of property information from the historical communication information to obtain the target property name includes: Performing contextual semantic integration on the historical communication information to obtain integrated communication information; Extracting property information from the integrated communication information to obtain an initial property name; In a case where the initial property listing name includes at least two property listing names, screening the at least two property listing names to determine the target property listing name; In the case that the initial property name includes a property name, the initial property name is determined to be the target property name.

4. The method for obtaining the property introduction script according to claim 1, characterized in that: Before determining the target property name, the method further includes: Determining a target broker based on the broker viewing data and / or the broker sales data, wherein the target broker is a broker who meets the requirements of an excellent broker and is screened based on the broker viewing data and / or the broker sales data; Extracting information about the target property listing corresponding to the target broker to obtain a correspondence between the property listing name and the introduction words, wherein the target property listing information corresponding to the target broker is used to represent the target broker's introduction of the property listing; The correspondence between the house source name and the house site identity is determined based on the house site dictionary technology, and then the correspondence between the house site identity and the introduction language is obtained based on the correspondence between the house site identity and the introduction language.

5. The method for obtaining a property introduction according to claim 4, characterized in that: The target property introduction information corresponding to the target broker is extracted to obtain a corresponding relationship between the property name and the introduction words, including: Extracting the target property introduction information to obtain the property name and the introduction words, wherein the property name includes the target community and the target property; Determining that the introduction speech includes the first information or the second information; If the introduction script includes first information, a correspondence between the target community and the introduction script is obtained, wherein the first information includes at least one of traffic information, geographical location, business district, building age, parking space, and surrounding facilities; If the introduction script includes second information, a corresponding relationship between the target property and the introduction script is obtained, and the second information includes at least one of area, floor, total price, decoration, and apartment type.

6. The method for obtaining the property introduction script according to claim 4, characterized in that: Before extracting the target property introduction information corresponding to the target broker to obtain the corresponding relationship between the property name and the introduction words, the method further includes: The target property introduction information corresponding to the target broker is obtained through a target communication channel, where the target communication channel includes at least one of an instant messaging tool, an enterprise chat tool, and an enterprise telephone call.

7. A device for acquiring a property introduction script, characterized in that: include: A property identification module is used to determine the target property name, where the target property name is the name of the property or community that the target customer has recently paid attention to; a script determination module, configured to determine at least one target introduction script corresponding to the target property name based on the target property name and a correspondence between the property name and the introduction script, wherein the correspondence between the property name and the introduction script is obtained by extracting property introduction information corresponding to outstanding agents; The result generation module is used to determine the final introduction words corresponding to the target property based on the at least one target introduction words.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method for obtaining the property introduction script as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for obtaining the property introduction script as described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for obtaining the property introduction script as described in any one of claims 1 to 6 is implemented.

Images