House resource matching information generation method and device, medium and program product

Abstract

The embodiment of the invention relates to a house resource matching information generation method and device, a medium and a program product, and the method comprises the steps: responding to a house resource matching information obtaining request, and determining a house resource region and a matching information type corresponding to the obtaining request; determining at least one retrieval text matched with the matched information type and the housing resource area; retrieving according to the at least one retrieval text to obtain a plurality of reference retrieval webpages; splitting webpage information contained in the plurality of reference retrieval webpages into a plurality of information fragments; and screening out a plurality of information fragments meeting a preset screening condition from the plurality of information fragments, and generating target housing resource matching information matched with the housing resource region and the matching information type according to the screened-out plurality of information fragments. According to the technical scheme, the house resource matching information can be automatically generated, and the generation quality and the generation efficiency of the house resource matching information are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer application technology, and in particular to a method, device, medium and program product for generating housing supporting information. Background Art

[0002] In the housing information construction scenario, there are multiple information interpretation modules for new houses. The information interpretation template interprets the housing's supporting information such as transportation and medical care.

[0003] In the related art, technical personnel collect and organize relevant information and compile the collected and organized relevant information into supporting information for housing resources. This method of obtaining supporting information for housing resources is not only inefficient, but also difficult to ensure the quality of the supporting information for housing resources. Summary of the Invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method, device, medium and program product for generating housing supporting information.

[0005] An embodiment of the present disclosure provides a method for generating supporting information for a housing source, comprising the following steps: in response to a request for obtaining supporting information for a housing source, determining a housing source region and a supporting information type corresponding to the request; determining at least one search text that matches the supporting information type and the housing source region; retrieving and obtaining a plurality of reference search web pages based on the at least one search text; splitting web page information contained in the plurality of reference search web pages into a plurality of information segments; screening out a plurality of information segments that meet preset screening conditions from the plurality of information segments, and generating target housing source supporting information that matches the housing source region and the supporting information type based on the screened out plurality of information segments.

[0006] The disclosed embodiment also provides a device for generating supporting information of a housing source, the device comprising: a first determination module for determining, in response to a request for obtaining supporting information of a housing source, the housing source region and the type of supporting information corresponding to the request; a second determination module for determining at least one search text that matches the supporting information type and the housing source region; an acquisition module for retrieving and obtaining a plurality of reference search web pages based on the at least one search text; a splitting module for splitting the web page information contained in the plurality of reference search web pages into a plurality of information segments; a screening module for screening out a plurality of information segments that meet preset screening conditions from the plurality of information segments; and an information generation module for generating target supporting information of a housing source that matches the housing source region and the supporting information type based on the screened out plurality of information segments.

[0007] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement a method for generating housing supporting information as provided in an embodiment of the present disclosure.

[0008] The embodiments of the present disclosure further provide a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method for generating housing supporting information as provided in the embodiments of the present disclosure.

[0009] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the above-mentioned method for generating housing supporting information when executed by a processor.

[0010] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art:

[0011] The scheme for generating ancillary information for a property in accordance with the disclosed embodiment responds to a request for ancillary information for a property, determines the property location and ancillary information type corresponding to the request, determines at least one search text matching the ancillary information type and property location, retrieves multiple reference search web pages based on the at least one search text, splits the webpage information contained in the multiple reference search web pages into multiple information segments, and then selects multiple information segments that meet preset screening conditions from the multiple information segments. Based on the selected multiple information segments, target ancillary information for the property is generated that matches the property location and ancillary information type. This technical solution automatically generates ancillary information for a property, improving the quality and efficiency of generating the ancillary information for a property. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0013] Figure 1 A flowchart of a method for generating housing supporting information provided by an embodiment of the present disclosure;

[0014] Figure 2 A flowchart of another method for generating housing supporting information provided by an embodiment of the present disclosure;

[0015] Figure 3 A schematic diagram of a scenario for generating housing supporting information provided by an embodiment of the present disclosure;

[0016] Figure 4A schematic diagram of the structure of a device for generating housing supporting information provided by an embodiment of the present disclosure;

[0017] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0019] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0020] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0021] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] In order to solve the above problems, the embodiments of the present disclosure provide a method for generating housing supporting information, which is introduced below in conjunction with specific embodiments.

[0025] Figure 1This is a flow chart of a method for generating property supporting information provided by an embodiment of the present disclosure. This method can be executed by a device for generating property supporting information, wherein the device can be implemented using software and / or hardware and can generally be integrated into an electronic device. Figure 1 As shown, the method includes:

[0026] Step 101: In response to a request for obtaining supporting information of a property, determine the property region and supporting information type corresponding to the request.

[0027] Among them, the supporting information of a property can be understood as information that interprets the property in any dimension. The property area refers to the geographical area where the property for which the supporting information is to be generated is located. For example, the property area can be "** City ** District", etc. The supporting information type refers to the specific information dimension of the property used to interpret the supporting information of the property, including but not limited to traffic information type, medical information type, terrain information type, etc. Among them, the supporting information type of the embodiment of the present disclosure can be one or more. When there are multiple supporting information types, the method for obtaining the supporting information of the property is the same for each supporting information type. Therefore, in the embodiment of the present disclosure, the acquisition of the supporting information of the property of one type of supporting information is focused on.

[0028] In an embodiment of the present disclosure, a request for obtaining supporting information of a property may be sent by a service end that displays the supporting information of the property, wherein the property area and the type of supporting information may be carried in the acquisition request, or after receiving the acquisition request, a request may be made to the corresponding service end to obtain the information.

[0029] Step 102: Determine at least one search text that matches the supporting information type and the housing area.

[0030] In an embodiment of the present disclosure, at least one search text matching the supporting information type and the housing listing area is determined, and each search text is used to retrieve a web page matching the supporting information type and the housing listing area.

[0031] It should be noted that in different application scenarios, the method of determining at least one search text that matches the supporting information type and the property location is different. Examples are as follows:

[0032] In some possible examples, at least one search text template matching each type of supporting information is pre-stored in a preset database. Each search text includes a search term corresponding to the corresponding supporting information type and a housing area field to be filled. As a possible example, when the supporting information type is transportation supporting information, the obtained search text template may include: "What buses are available in the ___ housing area?", "What subways are available in the ___ housing area?", etc., where "___" in the search text is the housing area field to be filled, and "What buses are available in the housing area?" and "What subways are available in the housing area?" are corresponding search terms, etc.

[0033] The housing area field of each search text template is filled with the housing area to determine at least one search text. Taking the above example, the search text obtained after filling may include "What buses are available in the housing area of ​​District B, City A?", "What subways are available in the housing area of ​​District B, City A?", etc.

[0034] In some possible examples, it is also possible to pre-train a retrieval text generation artificial intelligence model, input the supporting information type and housing area into the artificial intelligence model, and obtain at least one retrieval text output by the artificial intelligence model.

[0035] Step 103: retrieve and obtain a plurality of reference search web pages according to at least one search text.

[0036] Step 104: split the web page information contained in the multiple reference search web pages into multiple information segments.

[0037] After obtaining the search text, multiple reference search web pages are retrieved based on at least one search text. For example, each search text is input into a preset search platform for retrieval to obtain multiple reference search web pages fed back by the preset search platform.

[0038] Then, multiple information segments contained in the multiple reference search web pages are identified. In this embodiment, the web page information contained in the multiple reference search web pages is divided into multiple information segments. For example, each reference search web page is divided into paragraphs, and each paragraph is regarded as an information segment. Of course, in other possible embodiments, other methods can also be used to divide the reference search web pages into information segments.

[0039] In some possible embodiments, considering that the retrieved reference search web pages may be in large numbers, the reference search web pages are screened before identifying the multiple information fragments contained in the multiple reference search web pages.

[0040] In this embodiment, the first semantic similarity between each reference search web page and the corresponding search text can be calculated. For example, the text semantics of each search text can be identified, the web page semantics of each reference search web page can be identified, the text semantics can be matched with the web page semantics, and the first semantic similarity can be determined.

[0041] After calculating the first semantic similarity, all reference search web pages corresponding to each search text are sorted in descending order of the first semantic similarity to obtain a web page sorting result, and then, the first preset number of reference search web pages in the web page sorting result are screened out, and multiple reference search web pages are updated based on the screened reference search web pages, wherein the first preset number can be set as needed, that is, in this embodiment, for multiple reference search web pages corresponding to each search text, the first preset number of reference search web pages with high semantic similarity to the search text are screened, and other reference search web pages with low relevance are not involved in subsequent judgment.

[0042] Step 105 , screening out multiple information segments that meet preset screening conditions from the multiple information segments, and generating target housing source supporting information that matches the housing source area and supporting information type based on the screened multiple information segments.

[0043] In an embodiment of the present disclosure, after acquiring a plurality of information fragments, a plurality of information fragments satisfying a preset filtering condition are further filtered out from the plurality of information fragments.

[0044] In different application scenarios, the above preset screening conditions are different, as shown below:

[0045] Some possible examples include Figure 2 As shown, multiple information fragments that meet the preset screening conditions are screened out from multiple information fragments, including:

[0046] Step 201: obtain a preset supporting information segment template that matches the supporting information type, and determine a segment template feature corresponding to the supporting information segment template.

[0047] Among them, the supporting information segment template can also be stored in a preset database, wherein the supporting information segment template is a predetermined supporting information segment that meets the scene requirements (including style requirements, content requirements, etc.). In the embodiment of the present disclosure, a pre-set supporting information segment template that matches the supporting information type can be obtained, and the segment template features corresponding to the supporting information segment template can be determined, wherein the segment template features include but are not limited to the style features, semantic features, and information element types contained in the supporting information corresponding to the supporting information segment template.

[0048] Among them, the supporting information segment template can correspond to multiple search texts one by one, or can correspond to the supporting information type, that is, the search texts under the supporting information type correspond to the same supporting information segment template.

[0049] Step 202: extract reference segment features of each information segment.

[0050] In this embodiment, reference segment features of each information segment are also extracted, wherein the reference segment features include but are not limited to style features, semantic features, information element types contained in the supporting information, etc. corresponding to the information segment.

[0051] Step 203: Calculate the segment feature similarity between the segment template feature and the reference segment feature.

[0052] Step 204 : Filter out multiple information segments that meet preset filtering conditions from the multiple information segments based on segment feature similarities.

[0053] In an embodiment of the present disclosure, a segment feature similarity between a segment template feature and a reference segment feature is calculated, and based on the segment feature similarity, multiple information segments are screened out to select multiple information segments that meet preset screening conditions. The preset screening conditions may include: the segment feature similarity is greater than a preset segment feature similarity threshold, where the preset segment feature similarity threshold can be set according to the needs of the scenario; and / or the preset screening conditions may include: sorting the multiple information segments in descending order of segment feature similarity to obtain a first segment sorting result, where the first second preset number of segments are in the first segment sorting result. The second preset number can also be set according to the needs of the scenario.

[0054] In some possible examples, the semantic similarity S between each information segment and the corresponding search text can be calculated, and the information segments corresponding to each search text can be sorted in descending order of the semantic similarity S, and the first preset number of information segments in the sorting results are determined to be information segments that meet the preset screening conditions.

[0055] After filtering out the multiple information fragments, further, target property supporting information matching the property area and supporting information type is generated based on the multiple filtered information fragments, wherein the target property supporting information includes description content corresponding to the multiple filtered information fragments.

[0056] In some possible embodiments, multiple filtered information fragments can be input into a preset artificial intelligence model, wherein the preset artificial intelligence model pre-learns to generate corresponding housing supporting information based on the input information fragments, and obtains the target housing supporting information output by the preset artificial intelligence model.

[0057] In order to further ensure the generated target housing supporting information, a preset database can also be queried to determine reference housing supporting information that matches the housing area and supporting information type. The preset database stores some reference housing supporting information that matches the housing area and supporting information type with predetermined reliability. Therefore, before multiple filtered information fragments are input into the preset artificial intelligence model, the web page information contained in the filtered information fragments is also verified based on the reference housing supporting information, and the filtered information fragments that are inconsistent with the information contained in the reference housing supporting information are deleted. For example, if the reference housing supporting information contains the content "A district opened a total of 8 subway lines in 2023", and a filtered information fragment contains the content "A district opened a total of 6 subway lines in 2022", then because the content contained in the filtered information fragment does not match the reference housing supporting information, the corresponding filtered information fragment will be deleted.

[0058] In one embodiment of the present disclosure, in order to further ensure the reliability of the output target property supporting information, before generating the target property supporting information that matches the property area and supporting information type based on multiple filtered information fragments, the filtered information fragments may be filtered again.

[0059] For example, the second semantic similarity between each filtered information segment and the corresponding search text can be calculated, that is, the segment semantics of the filtered information segment can be identified, the text semantics of the search text can be calculated, and the similarity between the segment semantics and the text semantics can be calculated to obtain the second semantic similarity. All filtered information segments corresponding to each search text can be sorted in descending order of the second semantic similarity to obtain the second segment sorting result, and the first third preset number of information segments in the second segment sorting result can be filtered out, that is, the target housing supporting information can be generated only based on the filtered information segments.

[0060] Among them, corresponding target property supporting information can be generated according to multiple filtered information fragments corresponding to each search text. Therefore, when there are multiple search texts, multiple target property supporting information can be generated. After the target property supporting information is generated, the target property supporting information can be fed back to the business end, and the business end can select the target property supporting information from the multiple target property supporting information and fill it into the corresponding business module.

[0061] In one embodiment of the present disclosure, to facilitate data tracing, a webpage link to the webpage containing the filtered information fragments after generating the target property supporting information can also be determined. The generated target property supporting information and the corresponding webpage link can be displayed on the corresponding display interface to facilitate relevant personnel to verify whether the target property supporting information is reliable. If the relevant personnel determine that the target property supporting information is inconsistent with the webpage content corresponding to the webpage link, a model parameter adjustment request can be sent to control the preset artificial intelligence model to adjust the model parameters and regenerate the target property supporting information based on the corresponding filtered information fragments until reliable target property supporting information is obtained. Therefore, in this embodiment, adaptive optimization of the preset artificial intelligence model can also be achieved.

[0062] Based on the above embodiment, it can be known that the supporting information segment templates matching the same supporting information type can be one or more. When there are multiple supporting information segment templates, the method of generating corresponding target property supporting information for each supporting information type is the same as the above embodiment.

[0063] It should be noted that the search text in the embodiment of the present disclosure can be one or more. When there are multiple search texts, in order to improve the richness of the generated target property supporting information, corresponding target property supporting information can be generated for each search text. Thus, a corresponding filtered information fragment is generated for each search text. The following is an exemplary description with reference to a specific embodiment. In this example, the search text includes two:

[0064] Reference Figure 3 , by querying the preset database to determine two search text templates, and according to the search text templates, determine two search texts that match the supporting information type and the housing area, retrieve and obtain the reference search web page set W1 corresponding to the search text 1 on the preset search platform, and retrieve and obtain the reference search web page set W2 corresponding to the search text 2 on the preset search platform, calculate the first semantic similarity between each reference search web page in W1 and the search text 1, and screen out TOPn (n is a first preset number) reference search web page sets E1 based on the first semantic similarity, calculate the first semantic similarity between each reference search web page in W2 and the search text 2, and screen out TOPn (n is a first preset number) reference search web page sets E2 based on the first semantic similarity, divide E1 and E2 into segments, determine the information segment set R1 corresponding to E1, and determine the information segment set R2 corresponding to E2.

[0065] Query the preset database to determine the matching information segment template that matches the matching information type, calculate the segment feature similarity between each information segment in R1 and the matching information segment template, and filter out the filtered information segment set T1 in R1 based on the segment feature similarity. Calculate the segment feature similarity between each information segment in R2 and the matching information segment template, and filter out the filtered information segment set T2 in R2 based on the segment feature similarity.

[0066] Furthermore, the second semantic similarity between each filtered information segment in T1 and the search text 1 can be calculated, and a set of TOPm (m is a third preset number) filtered information segments Y1 can be further filtered out based on the second semantic similarity, and Y1 can be input into the corresponding preset artificial intelligence model to obtain the target housing supporting information corresponding to the search text 1. The second semantic similarity between each information segment in T2 and the search text 2 can be calculated, and a set of TOPm (m is a third preset number) information segments Y2 can be further filtered out based on the second semantic similarity, and Y2 can be input into the corresponding preset artificial intelligence model to obtain the target housing supporting information corresponding to the search text 1.

[0067] In summary, the method for generating ancillary information for a property in the disclosed embodiments responds to a request for ancillary information for a property, determines the property location and ancillary information type corresponding to the request, determines at least one search text that matches the ancillary information type and property location, retrieves multiple reference search web pages based on the at least one search text, splits the web page information contained in the multiple reference search web pages into multiple information segments, then filters out multiple information segments that meet preset filtering conditions from the multiple information segments, and generates target property ancillary information that matches the property location and ancillary information type based on the filtered multiple information segments. This technical solution automatically generates ancillary information for a property, improving the quality and efficiency of generating the ancillary information for a property.

[0068] In order to implement the above embodiment, the present disclosure also proposes a device for generating housing supporting information.

[0069] Figure 4 This is a schematic diagram of the structure of a device for generating housing supporting information provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Figure 4 As shown, the device includes: a first determination module 410, a second determination module 420, an acquisition module 430, a splitting module 440, a screening module 450, and an information generation module 460, wherein:

[0070] The first determining module 410 is configured to, in response to a request for obtaining supporting information of a property, determine the property region and supporting information type corresponding to the request;

[0071] The second determining module 420 is used to determine at least one search text that matches the supporting information type and the housing area;

[0072] An acquisition module 430 is configured to retrieve a plurality of reference search web pages according to at least one search text;

[0073] a splitting module 440 for splitting the web page information contained in the plurality of reference search web pages into a plurality of information segments;

[0074] A screening module 450 is configured to screen out a plurality of information segments that meet a preset screening condition from the plurality of information segments;

[0075] The information generation module 460 is used to generate target property supporting information that matches the property area and supporting information type based on the filtered multiple information fragments.

[0076] In one embodiment of the present disclosure, the second determining module 420 is configured to:

[0077] Querying a preset database to determine at least one search text template that matches the supporting information type, wherein each search text template includes a search term corresponding to the corresponding supporting information type and a property location field to be filled in;

[0078] The listing region field of each search text template is filled with the listing region to determine at least one search text.

[0079] In one embodiment of the present disclosure, the acquisition module 430 is configured to:

[0080] Each search text is input into the preset search platform for search, so as to obtain multiple reference search web pages fed back by the preset search platform.

[0081] In one embodiment of the present disclosure, the present invention further includes a webpage screening module for:

[0082] Calculating the first semantic similarity between each reference search web page and the corresponding search text;

[0083] Sorting all reference search web pages corresponding to each search text in descending order of the first semantic similarity to obtain a web page ranking result;

[0084] A first preset number of reference search web pages in the web page ranking result is screened out, and a plurality of reference search web pages are updated according to the screened reference search web pages.

[0085] In one embodiment of the present disclosure, the screening module 450 is configured to:

[0086] Obtaining a pre-set supporting information segment template that matches the supporting information type, and determining segment template features corresponding to the supporting information segment template;

[0087] Extracting reference segment features of each information segment;

[0088] Calculate the fragment feature similarity between the fragment template feature and the reference fragment feature;

[0089] A plurality of information segments that meet preset screening conditions are screened out from the plurality of information segments according to the segment feature similarity.

[0090] In one embodiment of the present disclosure, the preset screening conditions include:

[0091] The segment feature similarity is greater than a preset segment feature similarity threshold; and / or,

[0092] The first second preset number of the first fragment sorting results obtained in advance are located in the front, wherein the first fragment sorting results are obtained by sorting multiple information fragments in descending order of fragment feature similarity.

[0093] In one embodiment of the present disclosure, the present invention further includes a fragment screening module for:

[0094] Calculating the second semantic similarity between each filtered information segment and the corresponding search text;

[0095] sorting all the filtered information fragments corresponding to each search text in descending order of the second semantic similarity to obtain a second fragment sorting result;

[0096] The first third preset number of information segments in the second segment sorting result are filtered out.

[0097] In one embodiment of the present disclosure, the information generation module 460 is configured to:

[0098] Input multiple filtered information fragments into a preset artificial intelligence model, wherein the preset artificial intelligence model is pre-learned to generate corresponding housing supporting information based on the input information fragments.

[0099] Obtain target property supporting information output by the preset artificial intelligence model.

[0100] The device for generating supporting information of housing resources provided in the embodiments of the present disclosure can execute the method for generating supporting information of housing resources provided in any embodiment of the present disclosure, and has the functional modules and beneficial effects corresponding to the execution method.

[0101] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method for generating housing supporting information in the above embodiments.

[0102] An embodiment of the present disclosure provides an electronic device, which includes: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the steps of any method in the present disclosure.

[0103] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

[0104] The following specific reference Figure 5 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. The electronic device 500 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0105] like Figure 5 As shown, the electronic device 500 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a memory 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0106] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0107] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 509, or installed from the memory 508, or installed from the ROM 502. When the computer program is executed by the processor 501, the above-mentioned functions defined in the method for generating the housing supporting information of the embodiment of the present disclosure are performed.

[0108] In addition to the above-mentioned methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to perform the method provided by the embodiments of the present disclosure. The computer program product can be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present disclosure, and the programming languages ​​include object-oriented programming languages ​​such as Java, C++, etc., and also include conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0109] In addition, the embodiments of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, cause the processor to perform the method provided by the embodiments of the present disclosure. The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0110] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0111] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes any one of the methods described above.

[0112] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0113] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0114] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0115] It is understandable that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0116] 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 that includes 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 that includes the element.

[0117] The above are merely 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 limited to these embodiments, but is to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating housing supporting information, characterized in that: The following steps are involved: In response to a request for obtaining supporting information of a property, determining a property region and supporting information type corresponding to the request; Determining at least one search text that matches the supporting information type and the housing area; Retrieve and obtain a plurality of reference search web pages according to the at least one search text; Splitting the web page information contained in the plurality of reference search web pages into a plurality of information segments; A plurality of information segments that meet preset screening conditions are screened out from the plurality of information segments, and target housing source supporting information that matches the housing source area and the supporting information type is generated based on the screened plurality of information segments.

2. The method according to claim 1, wherein The determining of at least one search text that matches the supporting information type and the housing area includes: Querying a preset database to determine at least one search text template that matches the supporting information type, wherein each search text template includes a search term corresponding to the corresponding supporting information type and a property location field to be filled in; The property listing region field of each search text template is filled with the property listing region to determine the at least one search text.

3. The method according to claim 1, wherein Before splitting the webpage information contained in the plurality of reference search webpages into a plurality of information segments, the method further includes: Calculating a first semantic similarity between each reference search web page and the corresponding search text; Sorting all reference search web pages corresponding to each search text in descending order of the first semantic similarity to obtain a web page ranking result; A first preset number of reference search web pages in the web page ranking result are screened out.

4. The method according to claim 1, wherein The step of screening out a plurality of information fragments that meet a preset screening condition from the plurality of information fragments includes: Acquire a pre-set supporting information segment template that matches the supporting information type, and determine a segment template feature corresponding to the supporting information segment template; extracting reference segment features of each of the information segments; Calculating the segment feature similarity between the segment template feature and the reference segment feature; A plurality of information segments that meet the preset screening condition are screened out from the plurality of information segments according to the segment feature similarity.

5. The method according to claim 4, wherein The preset screening conditions include: The segment feature similarity is greater than a preset segment feature similarity threshold; and / or, The first second preset number of the first fragment sorting results obtained in advance are located in the first second preset number, wherein the first fragment sorting results are obtained by sorting the multiple information fragments in descending order of the fragment feature similarity.

6. The method according to any one of claims 1 to 5, characterized in that: Before generating target property supporting information that matches the property area and the supporting information type based on the filtered multiple information fragments, the method further includes: Calculating a second semantic similarity between each of the screened information segments and the corresponding search text; sorting all the filtered information fragments corresponding to each of the search texts in descending order of the second semantic similarity to obtain a second fragment sorting result; The first third preset number of information segments in the second segment sorting result is filtered out.

7. The method according to any one of claims 1 to 5, characterized in that: Generating target property supporting information that matches the property area and the supporting information type based on the filtered multiple information fragments includes: The screened multiple information fragments are input into a preset artificial intelligence model, wherein the preset artificial intelligence model is pre-learned to generate corresponding housing supporting information according to the input information fragments, Obtain the target housing supporting information output by the preset artificial intelligence model.

8. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for generating housing supporting information as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to execute the method for generating housing supporting information as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for generating housing supporting information as described in any one of claims 1 to 7.

Images