House resource searching method, electronic equipment, storage medium and program product

Abstract

The invention provides a housing resource searching method, electronic equipment, a readable storage medium and a computer program product. The housing resource searching method comprises the steps of obtaining a demand description text; performing semantic analysis on the demand description text to obtain a plurality of search conditions; performing label conversion on the plurality of search conditions to obtain a plurality of retrieval labels converted from the plurality of search conditions; and screening out a target housing resource from the plurality of to-be-selected housing resources, wherein the target housing resource is matched with the at least one retrieval tag.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a housing search method, electronic equipment, storage medium and program product. Background Art

[0002] Some real estate service platforms have real estate transaction or leasing businesses, and the database of the real estate service platform stores a large amount of house data for transaction or leasing. Usually, the house search function of the real estate service platform requires users to enter search conditions that meet its search rules. However, users usually cannot master the search rules of the real estate service platform and find it difficult to accurately convert their demand for houses into search conditions, making it difficult to search for satisfactory houses. Summary of the invention

[0003] The present disclosure provides a housing source search method, electronic device, storage medium and program product.

[0004] According to one aspect of the present disclosure, a housing search method is provided, comprising: obtaining a demand description text; performing semantic analysis on the demand description text to obtain multiple search conditions; performing label conversion on the multiple search conditions to obtain multiple search labels converted from the multiple search conditions; and screening out a target housing source from multiple housing sources to be selected, wherein the target housing source matches at least one of the search labels.

[0005] According to at least one embodiment of the present disclosure, a property search method is provided, and a requirement description text is obtained, including: sending a guide text to a user terminal, wherein the guide text includes at least one feature type of a property feature, and the guide text is used to guide the user to input a search text, and describe the property feature in the search text; obtaining the search text returned by the user terminal, and identifying the property feature in the search text; and in response to the search text containing the property feature, storing the search text as the requirement description text.

[0006] According to at least one embodiment of the housing search method of the present disclosure, obtaining the demand description text also includes: in response to the search text not containing the housing feature, sending a search text example to the user terminal, the search text example containing the housing feature.

[0007] According to at least one embodiment of the housing search method disclosed herein, obtaining a demand description text also includes: identifying blocked words in the search text; and in response to the search text containing the blocked words, blocking the search text and sending a blocked prompt text to the user terminal, wherein the blocked prompt text is used to guide the user to input the search text without the blocked words.

[0008] According to at least one embodiment of the housing search method disclosed herein, semantic analysis is performed on the demand description text to obtain multiple search conditions, including: feature extraction is performed on the demand description text to obtain multiple housing features in the demand description text and the feature type of each of the housing features; and text reorganization is performed on each of the housing features and their corresponding feature types to obtain the multiple search conditions.

[0009] According to the housing search method of at least one embodiment of the present disclosure, the housing search method further includes: in response to multiple search conditions including a commuting condition, filtering addresses matching the commuting condition from multiple housing addresses to obtain a target address; and filtering out housing sources with the address of the target address in a housing database to obtain the housing sources to be selected.

[0010] According to the housing search method of at least one embodiment of the present disclosure, a target address matching the commuting condition is screened from a plurality of housing addresses, including: extracting the commuting address, commuting type and commuting time from the commuting condition; determining a target address range according to the commuting address, commuting type and commuting time; and selecting the housing address within the target address range from the plurality of housing addresses to obtain the target address.

[0011] The housing search method according to at least one embodiment of the present disclosure further includes: sending a target housing set to the user terminal, the target housing set including at least one of the target housing; obtaining a feedback evaluation value returned by the user terminal, the magnitude of the feedback evaluation value representing the satisfaction with the target housing set; and in response to the feedback evaluation value being less than an evaluation threshold, sending a supplementary text to the user terminal, the supplementary text being used to guide the user to supplement new housing features in the demand description text.

[0012] According to another aspect of the present disclosure, an electronic device is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, so that the processor executes the housing search method of any embodiment of the present disclosure.

[0013] According to another aspect of the present disclosure, a readable storage medium is provided, wherein the readable storage medium stores execution instructions, and when the execution instructions are executed by a processor, the housing source search method of any embodiment of the present disclosure is used to implement.

[0014] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the housing search method of any embodiment of the present disclosure is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0016] Figure 1 It is a schematic diagram of an application scenario of a housing source search method according to an embodiment of the present invention.

[0017] Figure 2 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0018] Figure 3 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0019] Figure 4 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0020] Figure 5 It is a schematic diagram of an application scenario of a housing source search method according to an embodiment of the present invention.

[0021] Figure 6 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0022] Figure 7 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0023] Figure 8 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0024] Fig. 9 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0025] Fig.10 It is a flowchart of a housing source search method according to an embodiment of the present disclosure.

[0026] Fig.11 It is an interactive schematic flow chart of the housing source search method according to an embodiment of the present disclosure.

[0027] Fig.12 It is a schematic block diagram of the structure of a housing source search device according to an embodiment of the present disclosure.

[0028] Fig.13 It is a schematic block diagram of the structure of an electronic device equipped with a housing source search device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The present disclosure is further described in detail below in conjunction with the accompanying drawings and examples. It is understood that the specific examples described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0030] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] In the housing search application scenarios of some real estate service platforms, a large amount of housing data is stored in the housing database of the real estate service platform. How to conveniently help users find satisfactory housing among a large amount of housing data is an important challenge faced by the real estate service platform.

[0032] To facilitate the search of housing sources, the housing source data stored in the database is usually configured with corresponding tags, which are used to describe the characteristics of the housing source, such as apartment type, location, area, etc. In this way, when filtering housing sources using search conditions, you can filter out housing sources with specific tags to obtain housing sources with specific characteristics corresponding to specific tags.

[0033] In one solution, multiple optional filtering conditions are displayed on the property search page, and the user is required to set the filtering conditions for each label. For example, the user selects the filtering condition "less than 100 square meters" in the "Area" column, and selects the filtering condition "1" in the "Number of Bedrooms" column, and filters the properties by the above two filtering conditions. If the labels of a property include "1 bedroom" and "70 square meters", the property meets both of the above filtering conditions and can be filtered out. However, if the types of optional filtering conditions displayed on the property search page are too few, the number of filtered properties is still large, and the user is required to select the properties that meet the requirements one by one, which is inefficient. If there are too many types of optional filtering conditions displayed on the property search page, the user is required to configure each optional filtering condition one by one, which still has the disadvantage of low efficiency.

[0034] In another solution, the house search page has a text input box, and the user can enter the search criteria in the text input box to search for houses. However, the user has no way of knowing which criteria to enter for an effective search. For example, the user's need is to find a house with two bedrooms and one living room, and the search criteria "two bedrooms and one living room" are entered in the text input box. However, the houses in the database do not have a separately configured "two bedrooms and one living room" label, and the search results cannot be output. The user must enter the search criteria "2 bedrooms" and "1 living room" in the text input box respectively to search for houses with two bedrooms and one living room. This makes it difficult for users to accurately convert their needs into search criteria. In order to search for a satisfactory house, users often need to adjust the input search criteria multiple times and conduct multiple searches, resulting in low search efficiency.

[0035] To this end, the present disclosure proposes a housing source search method to solve the above problems.

[0036] Figure 1 The application scenario of the housing source search method of an embodiment of the present disclosure is shown. The application scenario illustrates the process of a user searching for housing sources on the housing source search page of the real estate service platform. The housing source search page has a text input box, and the user enters a text describing the demand for housing sources in natural language in the text input box. The real estate service platform performs semantic analysis on the text input by the user, parses the user's demand intention for housing sources, and obtains search conditions that characterize the user's demand intention. For example, the real estate service platform performs semantic analysis on the text "less than 13 million, Haidian District, two bedrooms and one living room, high floor, 30 minutes drive to Yuanmingyuan" input by the user, and obtains the search conditions "", "address in Haidian District", "number of bedrooms is 2", "number of living rooms is 1", "floor location is high". The above search conditions are converted into labels, and the obtained labels are shown in the "search item" column, including "region list = Haidian District", "house floor = high floor", "number of bedrooms = 2", "number of living rooms = 1", and "budget price = 0-13000000".

[0037] In summary, the real estate service platform can generate search conditions that meet the search rules of the real estate service platform by performing semantic analysis on the text input by the user, so as to match the corresponding tags according to the search conditions, thereby searching for houses with corresponding tags. In this way, the user only needs to enter the text describing the demand for houses in natural language, which is very easy to operate. The real estate service platform can intelligently convert the text input by the user into search conditions. The obtained search conditions can not only accurately describe the user's needs, but also meet the search rules of the real estate service platform. It can output multiple needs at the same time, and can efficiently and accurately obtain the search results of the house source.

[0038] For the convenience of description and to make the technical solutions of the specific implementation methods of the present disclosure easier to understand, before describing the housing source search method implemented in the present disclosure, the technical terms involved in the specific implementation methods of the present disclosure are defined as follows: Semantic Analysis refers to the process of deeply understanding and analyzing natural language texts to identify semantic information such as entities, relationships, and emotions in the texts.

[0039] Figure 2 FIG. 1 is a schematic diagram showing the overall process of a housing source search method M100 according to an embodiment of the present disclosure. Figure 2 The method shown includes steps S110 to S140. The method can be executed by electronic devices such as mobile phones and tablet computers.

[0040] Specifically, Figure 2 The methods shown include: S110. Obtain the requirement description text.

[0041] The demand description text is a text in which the user describes the demand for housing in natural language. The description of housing demand in natural language can directly and accurately reflect the user's demand for housing.

[0042] S120: Perform semantic analysis on the requirement description text to obtain multiple search conditions.

[0043] The purpose of semantic analysis of the demand description text is to convert the text input by the user in natural language into a language that the machine can understand, so that the machine can understand the user's intention. Among them, the search conditions can both represent the user's demand for housing and are in a language that the machine can understand, so that the machine can search for housing according to the search conditions.

[0044] In one example, a large language model (LLM) may be used to perform semantic analysis on the input requirement description text and output search conditions.

[0045] S130: Perform label conversion on the multiple search conditions to obtain multiple search labels converted from the multiple search conditions.

[0046] Among them, label conversion refers to converting search conditions into labels that can be recognized by the property database. In one example, all label data contained in the property database constitute labels in the label library. A search condition describes the feature value or feature range of a feature. A label in the label library represents a feature with a specific feature value. If a property has this label, then the property has the feature represented by this label. In this way, the property retrieved by the search label has the feature represented by the search label, and the search label is converted from the search condition. The feature represented by the search label is the feature described by the search condition, so that the property retrieved by the search label has the feature described by the search condition.

[0047] When performing label conversion, first determine whether the feature type of the feature described by the search condition is a feature type included in the feature library. If it is a feature type included in the feature library, then further extract the feature value described by the search condition, and combine the feature type of the feature described by the search condition to obtain a retrieval label. For example, if the search condition is "the number of bedrooms is 2", the feature type described is "the number of bedrooms", the feature value is "2", and the feature library contains the feature type "the number of bedrooms", then the retrieval label obtained by converting the search condition is "the number of bedrooms = 2". For another example, if the search condition is "the number of bathrooms is 2", the feature type described is "the number of bathrooms", the feature value is "2", but the feature library does not contain the feature type "the number of bathrooms", then the search condition cannot be converted into a retrieval label, because even if it is converted into a retrieval label in the format of "the number of bathrooms = 2", since none of the properties in the property database have a label of the feature "the number of bathrooms", the retrieval label cannot be used to retrieve properties in the property database.

[0048] In one example, the process of converting search conditions into labels and outputting retrieval labels can be embedded in the large language model, so that the large language model can perform a process of semantically analyzing the description text to obtain search conditions, and perform a process of converting search conditions into labels to obtain retrieval labels. The large language model that has been trained can output multiple retrieval labels according to the input requirement description text.

[0049] S140: Filter out a target property from multiple candidate properties, where the target property matches at least one search tag.

[0050] Among them, the properties to be selected are all or part of the properties in the property database. The properties to be selected match the search tags, which means that at least one tag of the properties to be selected matches the search tag. The tags of the properties to be selected match the search tags, which means that the feature type represented by the tag of the properties to be selected is the same as the feature type represented by the search tag, and the feature value of the tag of the properties to be selected is within the feature value range of the search tag. The properties to be selected that match the search tags are recorded as target properties.

[0051] For example, the search tag is "budget price = 0-13000000", the feature type of the search tag is "preset price", and the feature value is any value in "0-13000000"; assuming that a certain property to be selected has a tag "preset price = 10000000", its feature type is "preset price", which is the same as the feature type of the search tag, and the feature value is "10000000", within the feature value range of the search tag, then the tag "preset price = 10000000" of the property to be selected matches the search tag "budget price = 0-13000000", so that the property to be selected matches the search tag and is recorded as the target property. For another example, the search tag is "Number of bedrooms = 2", its feature type is "Number of bedrooms", and its feature value is a fixed value "2"; suppose a candidate property has a tag "Number of bedrooms = 1", its feature type is "Number of bedrooms", which is the same as the feature type of the search tag, and its feature value is "1", which is not within the feature value range of the search tag, then the candidate property does not match the search tag.

[0052] The property to be selected usually has multiple tags. When the number of search tags is one, if one of the multiple tags of the property to be selected matches the search tag, the property to be selected is considered to match the search tag. When the number of search tags is multiple, it can be configured as follows: when 1, 2, 3 or more tags of the property to be selected match the search tag, the property to be selected is the target property.

[0053] For example, if the number of search tags is 5, first try to filter out the candidate properties with 5 tags that can match the 5 search tags respectively as the target property. If the target property cannot be obtained, try to filter out the candidate properties with 4 tags that can match 4 of the 5 search tags as the target property. Similarly, assuming that the number of search tags is n, first try to filter out the candidate properties with n tags that can match the n search tags respectively as the target property. If the target property cannot be filtered out, relax the filtering conditions and filter out the candidate properties with n-1 tags that can match n-1 search tags among the n search tags as the target property.

[0054] In summary, the housing search method provided in this embodiment can perform semantic analysis on the demand description text of the user's search demand described in natural language, accurately refine the user's search demand to obtain the search conditions, and convert the search conditions into machine-recognizable search tags when performing the search, so as to filter out the target housing through the search tags. In this way, the user can describe the search demand in natural language to ensure the accuracy of the description of the search demand; in addition, the demand description text can be automatically converted into machine-recognizable search tags when performing the housing search, and the user does not need to learn how to convert the search demand into a usable search tag, eliminating the learning cost of the user to use the housing search function, and can greatly shorten the time from the user's raising the search demand to obtaining the search result, thereby improving the efficiency of the housing search.

[0055] Regarding step S110, in some embodiments of the present disclosure, it may include: Figure 3 Steps S1101 to S1103 are shown.

[0056] S1101. Send a guidance text to a user terminal, where the guidance text includes at least one feature type of a property feature.

[0057] Among them, the user end is the device end where the user inputs the search requirements when using the house search function. The house search method provided in this embodiment is executed on a cloud device. The cloud device obtains the search requirements from the user end and finally returns the search results (i.e., the target house) to the user end.

[0058] The search text is the text that the user enters on the user side to describe the search requirements. The guide text is the text sent from the cloud to the user side. The guide text is used to guide the user to enter the search text and describe the characteristics of the property in the search text.

[0059] Please combine Figure 1 , Figure 1 The page with a text input box in is a schematic diagram of the user-side page. In the user-side page, the text "Please describe the key information of the house you want to find, such as price, area, apartment type, etc." is a guide text, in which "price", "area" and "apartment type" are feature types of house features.

[0060] S1102: Obtain the search text returned by the user terminal, and identify the house source features in the search text.

[0061] Among them, the identifiable house source features in the search text are not limited to the house source features of the same type as the house source feature type contained in the guide text. In one example, a house source feature type dictionary is stored in the cloud, and the house source feature type dictionary includes multiple house source feature types. If the meaning of a word in the search text is recognized as belonging to the house source feature type in the house source feature type dictionary, then the word in the search text is recognized as a house source feature. For example, assuming that the house source feature types contained in the guide text are "price", "region" and "unit type", and the search text returned by the user end includes "high floor". Although the meaning of "high floor" does not belong to the above-mentioned house source feature types contained in the guide text, the house source feature type dictionary contains the house source feature type of "house floor", and the meaning of "high floor" belongs to this house source feature type, then it is finally recognized that the search text includes the house source feature of "high floor", and the type of this house source feature is "house floor".

[0062] S1103: In response to the search text containing a property feature, the search text is stored as a demand description text.

[0063] In one example, the property features in the property feature type dictionary are the set and feature types of the features represented by the tags of the properties in the property database. If the search text does not contain any property features, the search conditions cannot be extracted from the search text and converted into retrieval tags. In other words, not all search texts entered by the user can be used as demand description texts. Suppose the search text entered by the user is "find a house close to the road", but "close to the road" cannot be identified as a property feature, and there are no other property features in the search text, then the property cannot be searched based on the search text. In the case where the search text contains property features, it means that the property features in the search text can be extracted as search conditions and converted into retrieval tags, so that the search text can be stored as a demand description text, and the subsequent semantic analysis steps of the demand text can be performed.

[0064] In summary, steps S1101 to S1103 can ensure that good house features are obtained in the demand text, so as to ensure that the demand text can be semantically analyzed to obtain search conditions.

[0065] Regarding step S110, in some embodiments of the present disclosure, it may also include the following Figure 4 Steps S1101 to S1104 are shown. Steps S1101 to S1103 have been described above and will not be repeated here.

[0066] S1104: In response to the search text not containing the property feature, sending a search text example to the user terminal, wherein the search text example contains the property feature.

[0067] That is, the search text example uses specific property features as examples to guide users to enter search text containing property features. Figure 5 , Figure 5 The text area of ​​"You can search in this way" provides three search text examples. The first search text example is "less than 13 million, Haidian District, two bedrooms and one living room, high floor, 30 minutes drive to Yuanmingyuan", where "less than 13 million", "Haidian District", "two bedrooms", "one living room", "high floor", "to Yuanmingyuan", "drive" and "30 minutes" are all house features, and the corresponding house feature types are "budget price", "region list", "number of bedrooms", "number of living rooms", "house floor", "commuting address", "commuting type" and "commuting time".

[0068] In this way, step S1104 can further prompt the user how to enter text containing property features for property search when the search text entered by the user does not contain property features, so as to ensure that the search text entered by the user can be stored as requirement description text for property search.

[0069] Regarding step S110, in some embodiments of the present disclosure, it may also include the following Figure 6 Steps S1105 to S1106 are shown.

[0070] S1105: Identify blocked words in the search text.

[0071] The blocked words refer to the words included in the blocked word library. The words in the blocked word library can be added, modified or deleted according to the needs, and there is no restriction here.

[0072] S1106: In response to the search text containing a blocked word, the search text is blocked, and a blocking prompt text is sent to the user terminal.

[0073] The blocking prompt text is used to guide users to enter search text that does not contain blocked words. For example, the blocking prompt text can be "The xx word you entered does not comply with the platform regulations, please re-enter the information." For example, words that violate relevant regulations can be added to the blocked word library. If the search text contains words that violate relevant regulations, they can be promptly identified as blocked words, and the search text can be blocked in time to avoid the risk of violation caused by the retention of search text containing blocked words.

[0074] Regarding step S120, in some embodiments of the present disclosure, it may also include the following Figure 7 Steps S1201 to S1202 are shown.

[0075] S1201. Perform feature extraction on the demand description text to obtain multiple property features in the demand description text and a feature type of each property feature.

[0076] Feature extraction refers to extracting specific features from a piece of text content, and in some embodiments of the present disclosure, it specifically refers to extracting house features and obtaining feature types of the house features.

[0077] S1202: reorganize the text of each property feature and its corresponding feature type to obtain multiple search conditions.

[0078] Among them, text reorganization refers to reorganizing multiple words into a logically coherent sentence. In the embodiments of the present disclosure, it specifically refers to combining the extracted house features and house feature types into a logically coherent sentence.

[0079] For example, the demand description text is "less than 13 million, Haidian District, two bedrooms and one living room". Feature extraction is performed on the demand description text, and the house features obtained are "less than 13 million", "Haidian District", "two bedrooms" and "one living room", and the corresponding house feature types are "preset price", "house address", "number of bedrooms" and "number of living rooms". After text reorganization, the search conditions obtained are "budget price less than 13 million", "house address in Haidian District", "number of bedrooms is 2", and "number of living rooms is 1".

[0080] In some embodiments of the present disclosure, the house search method M100 further includes: Figure 8 Steps S150 and S160 are shown.

[0081] S150: In response to the multiple search conditions including a commuting condition, screen addresses matching the commuting condition from multiple housing source addresses to obtain a target address.

[0082] Among them, commuting conditions refer to the ability to reach the commuting address from the target address within the commuting time using a transportation method limited by the commuting type.

[0083] S160: Filter out houses with addresses equal to the target address in the house database to obtain houses to be selected.

[0084] If the multiple search conditions include the commuting condition, when determining the candidate housing sources, the housing sources with the target address in the housing source database are determined as the candidate housing sources. If the multiple search conditions do not include the commuting condition, any housing source in the housing source database can be selected as the candidate housing source.

[0085] Regarding step S150, in some embodiments of the present disclosure, it may include: Fig. 9 Steps S1501 to S1503 are shown.

[0086] S1501. Extract the commuting address, commuting type and commuting time from the commuting conditions.

[0087] For example, if the commuting condition is "drive to Yuanmingyuan for 30 minutes", then the commuting address can be extracted as "Yuanmingyuan", the commuting type is "drive", and the commuting time is "30 minutes".

[0088] S1502. Determine a target address range according to the commuting address, commuting type, and commuting time.

[0089] Among them, the target address range refers to the residential area that can be reached within the commuting time by the transportation mode specified by the commuting type.

[0090] S1503. Select a housing source address that is within the target address range from multiple housing source addresses to obtain the target address.

[0091] The house source database stores the house source address of each house source and the residential area where the house source address is located. If the residential area where a house source address is located is within the target address range, then the house source address is the target address.

[0092] In some embodiments of the present disclosure, the house search method M100 further includes: Fig.10 Steps S170 to S190 are shown.

[0093] S170: Send a target property set to the user terminal, where the target property set includes at least one target property.

[0094] The target property set is a set of target properties that meet the search requirements of the requirement description text. The target property set can be in the form of a list, text, picture, etc., and there is no restriction here.

[0095] S180: Obtain the feedback evaluation value returned by the user end.

[0096] The feedback evaluation value represents the degree of satisfaction with the target property set. The higher the feedback evaluation value, the higher the degree of satisfaction; conversely, the lower the feedback evaluation value, the lower the degree of satisfaction.

[0097] S190: In response to the feedback evaluation value being less than the evaluation threshold, sending a supplementary text to the user terminal.

[0098] The supplementary text is used to guide users to add new house features in the demand description text. For example, the supplementary text can be "Not satisfied with the result? You can also add the house information you want to find, such as floor height, area, north-south orientation, etc."

[0099] In summary, from step S170 to step S190, the user's satisfaction with the results of the property search (i.e., the target property set) can be judged by the feedback evaluation value, so that when the satisfaction level is low, a supplementary text can be sent to prompt the user to add new property features for retrieval, thereby providing more accurate property search results.

[0100] See also Fig.11 , Fig.11 The present invention illustrates a process of performing a house search on a house search platform by using the house search method according to an embodiment of the present invention.

[0101] First, the demand description text is obtained from the user end. Then, it is determined whether the demand description text contains blocked words. If it contains blocked words, a blocking prompt text is sent to the user end, and the demand description text is obtained from the user end again. In the case that the demand description text does not contain blocked words, the demand description text is semantically analyzed to obtain search conditions, and the search conditions are converted into search tags. At the same time, it is determined whether the search conditions include commuting conditions. In the case that the search conditions include commuting conditions, the target addresses matching the commuting conditions are screened out, and the selected housing sources are determined by the target addresses. In the case that the search conditions include commuting conditions, the selected housing sources are determined according to the default settings. Finally, the target housing source set is screened out from the selected housing sources using the search tags, and the target housing source set is sent to the user end. When the user end receives the searched target housing source, it can enter a feedback evaluation value to reflect the satisfaction with the search results. Then it is determined whether the feedback evaluation value is less than the evaluation threshold. In the case that the feedback evaluation value is less than the evaluation threshold, a supplementary text is sent to the user end to guide the user to add new housing source features to the demand description text and search for housing sources again. When the feedback evaluation value is greater than or equal to the evaluation threshold, it is considered that the user accepts the house search result.

[0102] Based on any of the above implementations, the present disclosure also provides a housing source search device. Fig.12 It is a schematic block diagram of the structure of a housing source search device according to an embodiment of the present disclosure.

[0103] like Fig.12 As shown, the house source search device includes: The text acquisition module 110 is used to acquire the requirement description text.

[0104] The semantic analysis module 120 is used to perform semantic analysis on the requirement description text to obtain multiple search conditions.

[0105] The tag conversion module 130 is used to perform tag conversion on multiple search conditions and obtain multiple search tags converted from the multiple search conditions.

[0106] The housing source search module 140 is used to filter out a target housing source from a plurality of candidate housing sources, where the target housing source matches at least one search tag.

[0107] Each of the above modules can be implemented by a computer program module. Fig.12 The house search device shown can be implemented based on a computer program module architecture.

[0108] In some embodiments of the present disclosure, the text acquisition module 110 is used to send a guide text to a user terminal, wherein the guide text includes at least one feature type of a property feature; obtain a search text returned by the user terminal, and identify property features in the search text; and in response to the search text containing property features, store the search text as a demand description text.

[0109] In some embodiments of the present disclosure, the text acquisition module 110 is further configured to send a search text example to a user terminal in response to the search text not containing a property feature, where the search text example contains the property feature.

[0110] In some embodiments of the present disclosure, the text acquisition module 110 is further used to identify blocked words in the search text; and in response to the search text containing blocked words, block the search text and send a blocking prompt text to the user terminal.

[0111] In some embodiments of the present disclosure, the semantic analysis module 120 is used to extract features from the demand description text to obtain multiple property features and feature types of each property feature in the demand description text; and to perform text reorganization on each property feature and its corresponding feature type to obtain multiple search conditions.

[0112] In some embodiments of the present disclosure, the housing search device also includes a commuting search module 150, which is used to respond to the inclusion of a commuting condition in multiple search conditions, filter addresses matching the commuting condition from multiple housing addresses to obtain a target address; and filter out housing sources with the target address in the housing database to obtain housing sources to be selected.

[0113] In some embodiments of the present disclosure, the commuting search module 150 is also used to extract the commuting address, commuting type and commuting time in the commuting conditions; determine the target address range according to the commuting address, commuting type and commuting time; and select a housing address within the target address range from multiple housing addresses to obtain the target address.

[0114] In some embodiments of the present disclosure, the housing search device also includes a feedback module 160, which is used to send a target housing set to a user terminal, where the target housing set includes at least one target housing; obtain a feedback evaluation value returned by the user terminal; and in response to the feedback evaluation value being less than an evaluation threshold, send supplementary text to the user terminal.

[0115] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0116] The executor of the housing source search method in the specific implementation manner of the present disclosure may be a mobile phone, a tablet computer, a server or other electronic device.

[0117] Therefore, based on any of the above embodiments, the present disclosure further provides an electronic device, which can execute the house search method of any of the embodiments described above in the present disclosure, and the house search device of any of the embodiments described above can be configured on the electronic device.

[0118] Fig.13 It is a schematic block diagram of the structure of an electronic device 1000 for house search equipped with a house search device according to an embodiment of the present disclosure.

[0119] The hardware structure of the electronic device 1000 can be implemented using a bus architecture. The bus architecture can include any number of interconnected buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 1100 connects various circuits including one or more processors 1200, memory 1300 and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0120] The bus 1100 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the figure only uses one connecting line, but does not mean that there is only one bus or one type of bus.

[0121] The present disclosure also provides a readable storage medium, in which a computer program is stored, and the computer program is used to implement the above method when executed by a processor. "Readable storage medium" can be any device that can contain, store, communicate, propagate or transmit a program for use in an instruction execution system, device or equipment or in combination with these instruction execution systems, devices or equipment. More specific examples of readable storage media include the following: an electrical connection portion (electronic device) with one or more wirings, a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM), etc.

[0122] The present disclosure also provides a computer program product. The method of the present disclosure can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed, the process or function of the present disclosure is executed in whole or in part.

[0123] A computer program or instruction may be stored in a readable storage medium or transmitted from one readable storage medium to another readable storage medium, for example, a computer program or instruction may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The readable storage medium may be any available medium that can be accessed or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid state drive. The computer readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0124] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment / method or example. Moreover, the specific features, structures, or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments / methods or examples described in this specification and features of different embodiments / methods or examples, unless they are contradictory.

[0129] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0130] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A housing source search method, characterized in that: include: Get the requirement description text; Performing semantic analysis on the requirement description text to obtain multiple search conditions; Performing label conversion on the plurality of search conditions to obtain a plurality of search labels converted from the plurality of search conditions; as well as A target property is screened out from a plurality of candidate properties, where the target property matches at least one of the search tags.

2. The housing source search method according to claim 1, characterized in that: Get the requirement description text, including: Sending a guide text to a user terminal, wherein the guide text includes at least one feature type of a property feature, and the guide text is used to guide the user to input a search text, and the property feature is described in the search text; Obtaining the search text returned by the user terminal, and identifying the house source features in the search text; and In response to the search text containing the house feature, the search text is stored as the demand description text.

3. The housing source search method according to claim 2, characterized in that: Get the requirement description text, including: In response to the search text not including the property feature, sending a search text example to the user terminal, wherein the search text example includes the property feature.

4. The housing source search method according to claim 2, characterized in that: Get the requirement description text, including: Identifying blocked words in the search text; and In response to the search text containing the blocked word, the search text is blocked, and a blocking prompt text is sent to the user terminal, wherein the blocking prompt text is used to guide the user to input the search text without the blocked word.

5. The housing source search method according to claim 1, characterized in that: Perform semantic analysis on the requirement description text to obtain multiple search conditions, including: Performing feature extraction on the demand description text to obtain multiple house source features in the demand description text and a feature type of each of the house source features; and Each of the house source features is reorganized with the corresponding feature type to obtain a plurality of search conditions.

6. The housing source search method according to claim 1, characterized in that: The housing source search method further includes: In response to the multiple search conditions including a commuting condition, filtering addresses matching the commuting condition from multiple housing source addresses to obtain a target address; and The house with the address being the target address is screened out from the house database to obtain the house to be selected.

7. The housing source search method according to claim 6, characterized in that: Filter the target address that matches the commuting conditions from multiple listing addresses, including: Extracting the commuting address, commuting type and commuting time in the commuting conditions; Determine a target address range according to the commuting address, commuting type and commuting time; and The house source address that is within the target address range is selected from the multiple house source addresses to obtain the target address.

8. The housing source search method according to claim 1, characterized in that: Also includes: Sending a target property set to the user terminal, wherein the target property set includes at least one target property; Acquire the feedback evaluation value returned by the user terminal, wherein the magnitude of the feedback evaluation value represents the satisfaction degree with the target housing source set; as well as In response to the feedback evaluation value being less than an evaluation threshold, a supplementary text is sent to the user terminal, wherein the supplementary text is used to guide the user to supplement new house source features in the demand description text.

9. An electronic device, characterized in that: include: A memory storing execution instructions; as well as A processor, wherein the processor executes the execution instructions stored in the memory, so that the processor executes the housing search method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores execution instructions, which are used to implement the housing search method according to any one of claims 1 to 8 when executed by the processor.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the housing search method according to any one of claims 1 to 8 is implemented.

Images