Title generation method and device and electronic equipment
By obtaining property information to determine the type of house and the highlights of similar properties, and generating and processing titles, the problem of mismatch between property listing titles and property information is solved, thus improving the user experience.
Patent Information
- Application Number
- CN202510570324.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-30
- Publication Date
- 2025-09-23
AI Technical Summary
The property listing outreach title does not match the property listing information, resulting in a poor user experience.
By obtaining property information, determining the type of property and highlights of similar properties, generating an initial title, and performing data verification and desensitization operations, the actual title is generated.
It improves the matching degree between the outreach title and the property information, avoids the problem of information inconsistency, and improves the user experience.
Smart Images
Figure CN120688489A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing technology, and in particular to a title generation method, device, and electronic device. Background Art
[0002] In the field of real estate brokerage, the outreach titles of property listings are usually manually written by the broker based on his or her own understanding of the content of the current property. As a result, the outreach titles may not match the information of the property itself, resulting in a poor user experience.
[0003] Therefore, how to improve the matching degree between outreach titles and properties has become an urgent problem to be solved. Summary of the Invention
[0004] In order to solve the above technical problems, the present disclosure provides a title generation method, device and electronic device.
[0005] In a first aspect, the present disclosure provides a title generation method, comprising: obtaining first property information of a property to be displayed; wherein the first property information includes at least a community name, a building, a unit, a room number, an orientation, and a unit type; based on the first property information, determining a house type and highlight information of similar properties that match the first property information; wherein the highlight information is used to indicate characteristic information of the similar properties; generating an initial title based on the house type, the highlight information, and the first property information; performing preprocessing based on the initial title and the first property information to obtain an actual title; wherein the preprocessing includes one or more of a data verification operation and a desensitization operation.
[0006] In a second aspect, the present disclosure provides a title generation device, comprising: an acquisition unit, configured to acquire first property information of a property to be displayed; wherein the first property information includes at least a community name, a building, a unit, a room number, an orientation, and a unit type; a processing unit, configured to determine, based on the first property information acquired by the acquisition unit, a house type and highlight information of similar properties that match the first property information; wherein the highlight information is used to indicate characteristic information of similar properties; the processing unit, further configured to generate an initial title based on the house type, the highlight information, and the first property information acquired by the acquisition unit; the processing unit, further configured to perform preprocessing based on the initial title and the first property information acquired by the acquisition unit to obtain an actual title; wherein the preprocessing includes one or more of a data verification operation and a desensitization operation.
[0007] In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement any one of the title generation methods provided in the first aspect when executing the computer program.
[0008] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising: a computer program stored on the computer-readable storage medium, wherein the computer program is executed by a controller to perform any of the title generation methods provided in the first aspect.
[0009] In a fifth aspect, the present invention provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute any one of the title generation methods provided in the first aspect.
[0010] These and other aspects of the present disclosure will become more apparent from the following description.
[0011] The technical solution provided by the present disclosure has the following advantages compared with the existing technology:
[0012] The title generation method provided by the present disclosure determines, upon obtaining first listing information for a property to be displayed, the property type and highlight information of similar listings matching the first listing based on the first listing information. The highlight information indicates characteristic information of similar listings. An initial title is generated based on the property type, highlight information, and the first listing information. By incorporating the highlight information of similar listings, it prevents agents from omitting information about the property to be displayed from the first listing. Subsequently, the initial title and the first listing information are preprocessed to generate an actual title. Because the actual title undergoes preprocessing of the initial title and the first listing information, such as data validation and desensitization, it avoids the appearance of the actual title being inconsistent with the first listing information. Furthermore, by incorporating the highlight information of similar listings into the initial title, it prevents agents from omitting information about the property to be displayed from the first listing. Consequently, the number of instances where the actual title does not match the property information is reduced, thereby improving the matching between the actual title and the property information, thus solving the problem of how to improve the matching between the outbound title and the property. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0014] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0015] Figure 1 exemplarily shows one of the flow charts of a title generation method provided in the first embodiment;
[0016] Figure 2 2 is a flow chart of a method for generating a title according to the first embodiment of the present invention;
[0017] Figure 3 FIG3 exemplarily shows a flowchart of a method for generating a title according to the first embodiment of the present invention;
[0018] Figure 4 4 is a flowchart of a method for generating a title according to the first embodiment of the present invention;
[0019] Figure 5 FIG5 exemplarily shows a flowchart of a method for generating a title according to the first embodiment of the present invention;
[0020] Figure 6 exemplarily shows a structural diagram of the title generating device provided in the second embodiment;
[0021] Figure 7 Schematic diagram of the structure of the electronic device provided in the third embodiment is shown in FIG. DETAILED DESCRIPTION
[0022] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.
[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0024] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.
[0025] Example 1
[0026] Figure 1The flowchart of the title generation method is shown in FIG. , and the execution subject of this example can be a server, such as Figure 1 As shown, the method includes:
[0027] S11. Obtain first property information of a property to be displayed, wherein the first property information includes at least a community name, a building, a unit, a room number, a direction, and a unit type.
[0028] In some examples, a server establishes a communication connection with an electronic device installed with a client. A user can then enter first listing information of a property to be displayed on the client, causing the electronic device to upload the first listing information to the server. The server can then generate an actual title based on the first listing information.
[0029] S12: Based on the first housing information, determine the housing type and highlight information of similar housing that matches the first housing information, wherein the highlight information is used to indicate characteristic information of the similar housing.
[0030] In some examples, based on the neighborhood name in the first housing listing information, a pre-configured storage relationship in the server's memory may be queried to determine the housing type corresponding to the neighborhood name, wherein the storage relationship includes a correspondence between the neighborhood name and the housing type.
[0031] In some examples, the server's memory pre-stores listing information for each displayed listing. Subsequently, the server can query the memory based on the first listing information to determine the highlights of similar listings that match the first listing information. For example, based on the first listing information, similar listings that match the first listing information are determined; second listing information and browsing data for the similar listings are obtained; and based on the first listing information, the second listing information, and browsing data, the highlights of similar listings that match the first listing information are determined.
[0032] Alternatively, the first property information is input into the recognition model for recognition to obtain the property type and highlight information. The training process of the recognition model includes:
[0033] Obtain first training sample data and a first labeling result of the first training sample data, wherein the first training sample data includes historical listing information of houses to be displayed, and the first labeling result includes house types and highlight information corresponding to the historical listing information of houses to be displayed.
[0034] The first training sample data is input into the first neural network model for learning to obtain a first prediction result of the first neural network model for the first training sample data.
[0035] Based on the first prediction result and the first labeling result, the network parameters of the first neural network model are adjusted until the first neural network model converges to obtain a recognition model.
[0036] In some examples, highlight information may be business district information, city information, urban area information, large living room, double south-facing, etc.
[0037] S13. Generate an initial title based on the house type, highlight information, and first house listing information.
[0038] In some examples, the property type, highlight information, and first property information can be input into the title model for processing to obtain a theoretical title, which is used as the initial title. The title model training process includes:
[0039] Obtain second training sample data and a second labeling result of the second training sample data; wherein the second training sample data includes historical housing information, the housing type and highlight information corresponding to the housing information, and the second labeling result includes a proposed title.
[0040] Inputting the second training sample data into the second neural network model for learning to obtain a second prediction result of the second neural network model;
[0041] Based on the second prediction result and the second labeling result, the network parameters of the second neural network model are adjusted until the second neural network model converges to obtain a title model.
[0042] In some examples, random sorting can be performed based on the house type, highlight information, and the first house information to obtain at least one candidate title; the similarity between the candidate title and the display title of the displayed house is calculated to obtain the click-through rate of the display title corresponding to the maximum similarity. Based on the click-through rate corresponding to each candidate title, the candidate title corresponding to the maximum click-through rate is determined to be the target title. Since the target title is randomly sorted based on the house type, highlight information, and the first house information, the readability of the target title may be poor. For this reason, the title generation method provided in the embodiment of the present disclosure generates an initial title by semantically processing the target title, thereby avoiding the problem of poor readability of the target title and ensuring the user experience.
[0043] In some examples, the first weight of the house type, the second weight of the highlight information, and the third weight of the first property information can be obtained; based on the first weight, the second weight, and the third weight, the display order of the house type, highlight information, and first property information and the display proportions of each comparison are determined; based on the display order, display proportion, house type, highlight information, and first property information, an initial title is generated.
[0044] In some examples, the sum of the first weight, the second weight, and the third weight is equal to 1.
[0045] S14: Preprocessing is performed based on the initial title and the first property information to obtain an actual title. The preprocessing includes one or more of a data verification operation and a sensitive word removal operation.
[0046] In some examples, based on the first property information, third property information of a displayed property is obtained; wherein, the displayed property and the property to be displayed have the same community name, orientation, and apartment type; data verification is performed on the first property information based on the third property information, and when it is determined that there are no filling errors in the first property information, the initial title is desensitized to obtain an updated title; and the updated title is used as the actual title.
[0047] In some examples, after generating the actual title, the server generates a prompt message containing the actual title. This prompt message indicates whether the user should use the actual title as the title of the listing to be displayed. In response to a confirmation operation on the actual title, the server sets the actual title as the title of the listing to be displayed and displays it. In response to a cancellation operation on the actual title, the server regenerates the actual title. The server stops generating the actual title until the user selects the actual title.
[0048] As can be seen from the foregoing, the title generation method provided by the disclosed embodiments, upon obtaining first listing information for a property to be displayed, determines the property type and highlight information of similar listings matching the first listing information based on the first listing information. The highlight information indicates characteristic information of similar listings. An initial title is generated based on the property type, highlight information, and the first listing information. By incorporating the highlight information of similar listings, it is possible to prevent agents from omitting information about the property to be displayed from the first listing information. Subsequently, the initial title and the first listing information are preprocessed to generate the actual title. Because the actual title undergoes preprocessing of the initial title and the first listing information, such as data validation and desensitization, it avoids the actual title appearing inconsistent with the first listing information. Furthermore, by incorporating the highlight information of similar listings into the initial title, it is possible to prevent agents from omitting information about the property to be displayed from the first listing information. Consequently, the number of instances where the actual title does not match the listing information is reduced, thereby improving the matching degree between the actual title and the listing information.
[0049] In some possible implementations, combining Figure 1 ,like Figure 2 As shown, the above S12 can be specifically implemented through the following S120 and S121.
[0050] S120. Determine the housing type based on the community name in the first housing source information; wherein the housing type includes at least school district housing and non-school district housing.
[0051] S121. Based on the first property information, determine highlight information of similar properties that match the first property information.
[0052] In some examples, the server's memory pre-stores the listing information for each displayed listing. Subsequently, based on the similarity (e.g., cosine similarity, Euclidean distance, etc.) between the first vector corresponding to the first listing information and the second vector corresponding to the listing information of the displayed listing, the displayed listing with the greatest similarity is determined to be a similar listing that matches the first listing information. Next, highlight keywords are extracted based on the description of the similar listing. For example, if the description contains the word "large living room," the highlight information of the similar listing is determined to include "large living room." Similarly, highlight information for similar listings that match the first listing information can be obtained.
[0053] As can be seen from the above, the title generation method provided by the disclosed embodiments determines the property type based on the neighborhood name in the first property listing information; based on the first property listing information, determines the highlights of similar properties that match the first property listing information. Subsequently, an initial title is generated based on the property type, the highlights, and the first property listing information. By incorporating the highlights of similar properties, it is possible to prevent agents from omitting information about the property to be displayed in the first property listing information. Subsequently, the initial title and the first property listing information are preprocessed to obtain the actual title. Because the actual title undergoes preprocessing of the initial title and the first property listing information, such as data validation and desensitization, it avoids the actual title appearing inconsistent with the first property listing information. Furthermore, because the highlights of similar properties are incorporated into the initial title, it is possible to prevent agents from omitting information about the property to be displayed in the first property listing information. Consequently, the number of instances where the actual title does not match the property listing information is reduced, thereby improving the matching degree between the actual title and the property listing information.
[0054] In some possible implementation examples, combined with Figure 1 ,like Figure 3 As shown, the above S12 can be specifically implemented through the following S122-S125.
[0055] S122. Determine the housing type based on the first housing information;
[0056] S123. Based on the first property information, determine similar properties that match the first property information;
[0057] S124: Obtain second property information of similar properties and browsing data of similar properties.
[0058] In some examples, browsing data of similar properties can be obtained from the user's access data stored in the server.
[0059] S125. Determine highlight information of similar properties that match the first property information based on the first property information, the second property information, and the browsing data; wherein the feature information includes at least business district information.
[0060] As can be seen from the above, the title generation method provided by the embodiments of the present disclosure determines the property type based on first property information; determines similar properties matching the first property information based on the first property information; and obtains second property information and browsing data for the similar properties. Based on the first property information, the second property information, and browsing data, highlights of the similar properties matching the first property information are determined. By incorporating the highlights of the similar properties, brokers are prevented from omitting information about the property to be displayed in the first property information. Subsequently, the initial title and the first property information are preprocessed to generate the actual title. Because the actual title undergoes preprocessing of the initial title and the first property information, such as data validation and desensitization, it avoids the actual title appearing inconsistent with the first property information. Furthermore, by incorporating the highlights of the similar properties into the initial title, brokers are prevented from omitting information about the property to be displayed in the first property information. Consequently, the number of instances where the actual title does not match the property information is reduced, thereby improving the matching degree between the actual title and the property information.
[0061] In some possible implementation examples, combined with Figure 1 ,like Figure 4 As shown, the above S13 can be specifically implemented through the following S130-S132.
[0062] S130, obtaining a first weight of the house type, a second weight of the highlight information, and a third weight of the first house information;
[0063] In some examples, different weight distribution relationship tables are configured for different housing types, different highlight information, and different first housing listing information. Furthermore, the server reads the weight distribution relationship table stored in a memory and queries the weight distribution relationship table based on the housing type, highlight information, and first housing listing information to determine a first weight for the housing type, a second weight for the highlight information, and a third weight for the first housing listing information.
[0064] For example, the weight distribution relationship table is shown in Table 1.
[0065] Table 1
[0066]
[0067] Thus, when the server obtains the property type, highlight information, and the first listing information, it queries the weight distribution relationship table to determine the first weight of the property type, the second weight of the highlight information, and the third weight of the first listing information. For example, if the property type is a school district property, the highlight information includes information 1 and information 2, the number of rooms in the first listing is a1, the area of the listing to be displayed is greater than b1, and the query is c1, querying Table 1 shows that the first weight is w1, the second weight is w2, and the third weight is w3.
[0068] S131. Determine the display order of the house type, highlight information, and first property information, and the display proportions thereof for comparison, based on the first weight, the second weight, and the third weight.
[0069] S132: Generate an initial title based on the display order, display ratio, house type, highlight information, and first house information.
[0070] In some examples, to prevent the initial title from being too long, resulting in the user not being able to fully read the displayed title, the server pre-configures a maximum number of characters in the initial title. The server then determines the displayable character count of the target content based on the product of the maximum number and the display percentage. The target content includes any of the following: property type, highlight information, and the first property listing. A title template is then generated based on the display order and the displayable character count of the target content. A title template with a character padding value corresponding to the target content is selected to generate a candidate title. The similarity between the candidate title and the displayed title of the displayed property listing is then calculated, and the click-through rate (CTR) of the title with the highest similarity is determined. Based on the CTR corresponding to each candidate title, the candidate title with the highest CTR is determined as the target title. Because the target title is randomly sorted based on property type, highlight information, and the first property listing, it may be difficult to read. Therefore, the title generation method provided in the present disclosure generates an initial title by semantically processing the target title, thereby avoiding this problem and ensuring a better user experience.
[0071] As can be seen from the above, the title generation method provided by the embodiment of the present disclosure, when generating the initial title, obtains the first weight of the house type, the second weight of the highlight information and the third weight of the first property information; based on the first weight, the second weight and the third weight, determines the display order corresponding to the house type, the highlight information and the first property information and the display proportions of each comparison. Generate an initial title based on the display order, display proportion, house type, highlight information and the first property information. Since the actual title has undergone pre-processing of the initial title and the first property information, such as data verification operations and desensitization operations, the problem of the actual title not being consistent with the first convenient information can be avoided; at the same time, since the highlight information of similar properties is introduced into the initial title, it can avoid the broker missing some information of the property to be displayed in the first property information. Therefore, the number of times the actual title does not match the property information will be reduced, and the matching degree of the actual title and the property information can be improved.
[0072] In some feasible examples, preprocessing includes data verification and desensitization operations; combined with Figure 1 ,like Figure 5 As shown, the above S14 can be specifically implemented through the following S140-S142.
[0073] S140. Based on the first housing information, obtain third housing information of the displayed housing; wherein the displayed housing and the housing to be displayed have the same community name and apartment type.
[0074] S141. Perform data verification on the first property information based on the third property information. When it is determined that there are no errors in the first property information, perform a desensitizing operation on the initial title to obtain an updated title.
[0075] In some examples, because the listing to be displayed and the already displayed listing share the same residential community name and the same apartment type, the listing information for both should be consistent. To prevent brokers from entering incorrect first listing information, the title generation method provided in the disclosed embodiments performs data verification on the first listing information based on the third listing information. For example, if the number of rooms in the first listing information differs from the number of rooms in the third listing information, the number of rooms in the first convenience information is modified to the number of rooms in the third listing information. Alternatively, if the orientation in the first listing information differs from the orientation in the third listing information, the orientation in the first convenience information is modified to the orientation in the third listing information. This avoids the problem of brokers entering incorrect first listing information and improves the user experience.
[0076] S142. Use the updated title as the actual title.
[0077] As can be seen from the above, the title generation method provided by the embodiment of the present disclosure, when generating the initial title, introduces the highlights of similar properties, thereby preventing the broker from omitting some information about the property to be displayed in the first property information. Subsequently, based on the first property information, third property information of the displayed property is obtained; data verification is performed on the first property information based on the third property information. When it is determined that there are no errors in the first property information, the initial title is desensitized to obtain an updated title; and the updated title is used as the actual title. Because the actual title has undergone preprocessing of the initial title and the first property information, such as data verification and desensitization, it can avoid the actual title appearing inconsistent with the first convenient information. At the same time, because the initial title introduces the highlights of similar properties, it can prevent the broker from omitting some information about the property to be displayed in the first property information. Therefore, the number of times the actual title does not match the property information is reduced, thereby improving the matching degree between the actual title and the property information.
[0078] Example 2
[0079] The structural diagram of the title generation device provided in the second embodiment of the present application is as follows: Figure 6 The title generating device shown includes: an acquisition unit 201 and a processing unit 202.
[0080] The acquisition unit 201 is configured to acquire first property information of a property to be displayed; wherein the first property information includes at least a community name, a building, a unit, a room number, a direction, and a unit type;
[0081] Processing unit 202 is configured to determine, based on the first housing information obtained by obtaining unit 201, the housing type and highlight information of similar housing that matches the first housing information; wherein the highlight information is used to indicate characteristic information of the similar housing;
[0082] The processing unit 202 is further configured to generate an initial title based on the house type, highlight information, and the first house information obtained by the obtaining unit 201;
[0083] The processing unit 202 is further configured to perform preprocessing based on the initial title and the first property information obtained by the obtaining unit 201 to obtain an actual title; wherein the preprocessing includes one or more of a data verification operation and a desensitization operation.
[0084] In some feasible examples, the processing unit 202 is specifically used to determine the housing type based on the community name in the first housing information obtained by the obtaining unit 201; wherein the housing type includes at least school district housing and non-school district housing.
[0085] In some feasible examples, the processing unit 202 is specifically used to determine similar properties that match the first property information based on the first property information obtained by the acquisition unit 201; the acquisition unit 201 is specifically used to obtain second property information of similar properties and browsing data of similar properties; the processing unit 202 is specifically used to determine highlight information of similar properties that match the first property information based on the first property information, the second property information and browsing data obtained by the acquisition unit 201; wherein the characteristic information includes at least business district information.
[0086] In some feasible examples, the acquisition unit 201 is specifically used to obtain the first weight of the house type, the second weight of the highlight information, and the third weight of the first property information; the processing unit 202 is specifically used to determine the display order of the house type, highlight information, and first property information and the display proportions for comparison based on the first weight, second weight, and third weight obtained by the acquisition unit 201; the processing unit 202 is specifically used to generate an initial title based on the display order, display proportion, house type, highlight information, and first property information.
[0087] In some feasible examples, preprocessing includes data verification operations and desensitization operations; the processing unit 202 is specifically used to control the acquisition unit 201 to obtain third housing information of the displayed display housing based on the first housing information obtained by the acquisition unit 201; wherein the display housing and the housing to be displayed have the same community name and apartment type; the processing unit 202 is specifically used to perform data verification on the first housing information based on the third housing information obtained by the acquisition unit 201, and when it is determined that there are no filling errors in the first housing information, perform a desensitization operation on the initial title to obtain an updated title; the processing unit 202 is specifically used to use the updated title as the actual title.
[0088] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.
[0089] Of course, the title generation apparatus provided by the embodiment of the present invention includes but is not limited to the above modules. For example, the title generation apparatus may further include a storage unit 203. The storage unit 203 may be used to store program code of the title generation apparatus and may also be used to store data generated during operation of the title generation apparatus, such as diagnostic data.
[0090] Example 3
[0091] A third embodiment of the present invention provides a schematic diagram of the structure of an electronic device, such as Figure 7 The electronic device shown may include: at least one processor 51 , a memory 52 , a communication interface 53 and a communication bus 54 .
[0092] The following is a detailed introduction to the various components of electronic equipment:
[0093] The processor 51 is the control center of the electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor 51 is a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more DSPs or one or more field programmable gate arrays (FPGAs).
[0094] In a specific implementation, as an embodiment, the processor 51 may include one or more CPUs, such as CPU0 and CPU1 included in the CPU. Also, as an embodiment, the electronic device may include multiple processors, such as the CPU including processor 51 and processor 55. Each of these processors may be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).
[0095] The memory 52 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 52 may be independent and connected to the processor 51 via a communication bus 54. The memory 52 may also be integrated with the processor 51.
[0096] In a specific implementation, the memory 52 is used to store the data of the present invention and execute the software program of the present invention. The processor 51 can execute various functions of the air conditioner by running or executing the software program stored in the memory 52 and calling the data stored in the memory 52.
[0097] The communication interface 53 uses any transceiver or other device for communicating with other devices or communication networks, such as a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), a terminal, the cloud, etc. The communication interface 53 may include an acquisition unit to implement the acquisition function.
[0098] Communication bus 54 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, a single thick line is used, but this does not imply that there is only one bus or only one type of bus.
[0099] As an example, combining Figure 6 The function implemented by the acquisition unit 201 of the title generation device is the same as that of the communication interface 53, the function implemented by the processing unit 202 in the title generation device is the same as that of the processor 51, and the function implemented by the storage unit 203 in the title generation device is the same as that of the memory 52.
[0100] Example 4
[0101] A fourth embodiment of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method in any embodiment.
[0102] Example 5
[0103] A fifth embodiment of the present invention provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute any method of any embodiment.
[0104] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.
Claims
1. A method for generating a title, characterized in that: include: Obtaining first property information of a property to be displayed; wherein the first property information includes at least a community name, building, unit, room number, orientation, and apartment type; Based on the first housing information, determine the housing type and highlight information of similar housing that matches the first housing information; wherein the highlight information is used to indicate characteristic information of the similar housing; generating an initial title based on the house type, the highlight information, and the first house listing information; Preprocessing is performed based on the initial title and the first property information to obtain an actual title; wherein the preprocessing includes one or more of a data verification operation and a desensitization operation.
2. The title generation method according to claim 1, characterized in that The determining of the housing type based on the first housing information includes: Based on the community name in the first housing information, determine the housing type; wherein the housing type includes at least school district housing and non-school district housing.
3. The title generation method according to claim 1, wherein: The determining, based on the first property information, highlight information of similar properties that match the first property information includes: Based on the first property information, determining similar properties that match the first property information; Obtaining second listing information of the similar listing and browsing data of the similar listing; Based on the first property information, the second property information and the browsing data, highlight information of similar properties that match the first property information is determined; wherein the feature information includes at least business district information.
4. The title generation method according to claim 1, wherein: The generating of an initial title based on the house type, the highlight information, and the first house listing information includes: Obtain a first weight of the house type, a second weight of the highlight information, and a third weight of the first house information; Based on the first weight, the second weight, and the third weight, determining a display order corresponding to the house type, the highlight information, and the first house listing information, and a display proportion for comparison thereof; The initial title is generated based on the display order, the display proportion, the house type, the highlight information and the first house information.
5. The title generation method according to claim 1, wherein: The preprocessing includes data verification and desensitization operations; The preprocessing based on the initial title and the first property information to obtain the actual title includes: Based on the first housing information, obtaining third housing information of a displayed housing, wherein the displayed housing and the housing to be displayed have the same community name and apartment type; performing data verification on the first property information based on the third property information, and upon determining that there are no errors in the first property information, performing a desensitizing operation on the initial title to obtain an updated title; The update title is used as the actual title.
6. A title generating device, characterized in that: include: An acquisition unit, configured to acquire first property information of a property to be displayed; wherein the first property information includes at least a community name, a building, a unit, a room number, a direction, and a unit type; a processing unit, configured to determine, based on the first housing information acquired by the acquiring unit, a housing type and highlight information of similar housing listings that match the first housing information; wherein the highlight information is used to indicate characteristic information of the similar housing listings; The processing unit is further configured to generate an initial title based on the house type, the highlight information, and the first house information acquired by the acquiring unit; The processing unit is further configured to perform preprocessing based on the initial title and the first property information obtained by the acquisition unit to obtain an actual title; wherein the preprocessing includes one or more of a data verification operation and a desensitization operation.
7. The title generating device according to claim 6, characterized in that The processing unit is specifically configured to determine a housing type based on a community name in the first housing source information acquired by the acquisition unit; wherein the housing type includes at least school district housing and non-school district housing.
8. The title generating device according to claim 6, characterized in that The processing unit is specifically configured to determine similar properties that match the first property information based on the first property information acquired by the acquiring unit; The acquiring unit is specifically configured to acquire the second property information of the similar property and the browsing data of the similar property; The processing unit is specifically configured to determine highlight information of similar properties that match the first property information based on the first property information, the second property information, and the browsing data acquired by the acquisition unit; wherein the feature information includes at least business district information.
9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the title generation method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the title generation method according to any one of claims 1 to 6 when executed by a processor.