House evaluation method, house search method, electronic equipment and storage medium

Abstract

The invention provides a house evaluation method, a house search method, an electronic device and a storage medium, the house evaluation method comprises the following steps: collecting sensibility description information of a to-be-evaluated house, the sensibility description information being used for describing a use experience feeling of the to-be-evaluated house; cleaning processing is carried out on the basis of the sensibility description information, target sensibility description information is obtained, and the target sensibility description information is information obtained after cleaning processing of de-duplication and / or invalid information removal is carried out on the sensibility description information; according to the target sensibility description information, the to-be-evaluated house is evaluated, a sensibility evaluation text of the to-be-evaluated house is obtained, and the sensibility evaluation text is a text for evaluation description from the use experience feeling dimension. The subjective feeling description of the house can be comprehensively depicted, so that the customer can obtain the experience feeling after check-in before check-in, and the proper house can be more accurately matched.

Description

Technical Field

[0001] The present invention relates to the technical field of house evaluation, and in particular to a house evaluation method, a house search method, an electronic device and a storage medium. Background Art

[0002] In the current real estate market, real estate agents play a crucial role as the bridge between listings and buyers. However, they face certain limitations when searching for properties. Traditionally, agents rely primarily on precise, objective data such as location, square footage, number of rooms, and price range. While this search method effectively identifies properties that meet basic requirements, it struggles to capture the more nuanced and subjective experience needs of homebuyers.

[0003] Therefore, finding a house evaluation method that can comprehensively describe the subjective feeling of a house and match it with customers has become a current research hotspot. Summary of the Invention

[0004] The present invention provides a house evaluation method, a house search method, an electronic device and a storage medium, which can achieve a comprehensive description of the subjective experience of a house, thereby ensuring that customers can obtain the experience after moving in before moving in, and can more accurately match suitable houses.

[0005] The present invention provides a house evaluation method, which includes: collecting perceptual description information of a house to be evaluated, wherein the perceptual description information is used to describe the user experience of the house to be evaluated; performing cleaning processing based on the perceptual description information to obtain target perceptual description information, wherein the target perceptual description information is information obtained by performing cleaning processing on the perceptual description information to remove duplicates and / or invalid information; and evaluating the house to be evaluated based on the target perceptual description information to obtain a perceptual evaluation text of the house to be evaluated, wherein the perceptual evaluation text is a text that describes the evaluation from the dimension of user experience.

[0006] According to a house evaluation method provided by the present invention, the perceptual description information of the house to be evaluated is obtained in the following manner: objective attribute description information of the house to be evaluated is obtained, wherein the objective attribute description information is used to describe the objective physical attributes of the house to be evaluated; and based on the objective attribute description information of the house to be evaluated, perceptual description information of the house to be evaluated that matches the objective attribute description information is obtained.

[0007] According to a house evaluation method provided by the present invention, the sensitivity description information of the house to be evaluated is obtained in the following manner: initial sensitivity description information of the house to be evaluated by different role users is obtained respectively; the evaluation weight of each role user is determined based on the degree of association between the different role users and the house to be evaluated; and the sensitivity description information of the house to be evaluated is obtained by performing weighted processing based on the evaluation weight of each role user and the initial sensitivity description information of the house to be evaluated by each role user.

[0008] The present invention also provides a house search method, which includes: obtaining a user's house search information, wherein the house search information is search information under the experience and feeling dimension; based on the house search information and various perceptual evaluation texts about each house, screening out a target house that matches the house search information from a plurality of the houses, wherein the various perceptual evaluation texts for each house are determined using any one of the house evaluation methods described.

[0009] According to a house search method provided by the present invention, the sensitivity evaluation text is a sensitivity evaluation text sentence; the method of screening a target house matching the house search information from a plurality of houses based on the house search information and the sensitivity evaluation texts about each house specifically includes: determining a first text vector corresponding to the house search information based on the house search information; determining second text vectors corresponding to each sensitivity evaluation text sentence based on each sensitivity evaluation text sentence; respectively calculating each vector distance between the first text vector and each second text vector; using the sensitivity evaluation text sentence corresponding to the minimum vector distance as the target sensitivity evaluation text sentence; and using the house corresponding to the target sensitivity evaluation text sentence as the target house matching the house search information.

[0010] According to a house search method provided by the present invention, the sensitivity evaluation text is a sensitivity evaluation text keyword; the method, based on the house search information and the sensitivity evaluation texts about each house, screens out a target house matching the house search information from a plurality of houses, specifically comprising: determining a search keyword matching the house search information based on the house search information; determining a target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword; and using the house corresponding to the target sensitivity evaluation text keyword as the target house matching the house search information.

[0011] According to a house search method provided by the present invention, each of the sensitivity evaluation texts includes multiple sensitivity evaluation text keywords; based on the similarity between the search keyword and each of the sensitivity evaluation text keywords, a target sensitivity evaluation text keyword with the highest similarity to the search keyword is determined, specifically comprising: clustering the multiple sensitivity evaluation text keywords to obtain the sensitivity evaluation text keywords under each cluster cluster; based on the number of sensitivity evaluation text keywords under each cluster cluster, the level of each cluster cluster is determined, and cluster cluster keywords are set for cluster clusters of each level, wherein the number of sensitivity evaluation text keywords under the cluster cluster is positively correlated with the level of the cluster cluster; the cluster cluster keywords are determined according to the sensitivity evaluation text keywords under the cluster cluster; based on the similarity between the search keyword and the cluster cluster keywords of each highest-level cluster cluster, a target cluster cluster keyword with the highest similarity to the search keyword is determined; and the target cluster cluster keyword is used as the target sensitivity evaluation text keyword with the highest similarity to the search keyword.

[0012] The present invention also provides a house evaluation system, which includes: a collection module for collecting sensory description information of the house to be evaluated, wherein the sensory description information is used to describe the user experience of the house to be evaluated; a processing module for performing cleaning processing based on the sensory description information to obtain target sensory description information, wherein the target sensory description information is the information after the sensory description information is cleaned by deduplication and / or removal of invalid information; an evaluation module for evaluating the house to be evaluated based on the target sensory description information to obtain a sensory evaluation text of the house to be evaluated, wherein the sensory evaluation text is a text that evaluates and describes the house from the dimension of user experience.

[0013] The present invention also provides a house search system, which includes: an acquisition module for acquiring a user's house search information, wherein the house search information is search information under the experience and perception dimension; a search module for screening a target house to be evaluated that matches the house search information from a plurality of houses to be evaluated based on the house search information and various perceptual evaluation texts about each house to be evaluated, wherein the various perceptual evaluation texts of each house to be evaluated are determined using any one of the house evaluation methods described.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements any one of the above-described house evaluation methods and any one of the above-described house search methods.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements any of the above-mentioned house evaluation methods and any of the above-mentioned house search methods.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-mentioned house evaluation methods and any one of the above-mentioned house search methods.

[0017] The present invention provides a housing evaluation method, a housing search method, an electronic device, and a storage medium. The method comprises: collecting perceptual description information of a housing to be evaluated, wherein the perceptual description information is used to describe the user experience of the housing to be evaluated; performing cleaning processing based on the perceptual description information to obtain target perceptual description information; and evaluating the housing to be evaluated based on the target perceptual description information to obtain a perceptual evaluation text of the housing to be evaluated, wherein the perceptual evaluation text is a text describing the evaluation from the perspective of user experience. This method achieves a comprehensive description of the subjective perceptual experience of the housing, thereby ensuring that customers can obtain their experience of the housing before moving in, and more accurately matching them with suitable housing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a flow chart of the housing evaluation method provided by the present invention.

[0020] Figure 2 It is a flow chart of the house search method provided by the present invention.

[0021] Figure 3 This is one of the flowcharts provided by the present invention for screening a target house matching the house search information from a plurality of houses based on the house search information and the various perception evaluation texts about the houses.

[0022] Figure 4 This is the second flow chart of the present invention for screening a target house matching the house search information from a plurality of houses based on the house search information and the perceptual evaluation texts about the houses.

[0023] Figure 5It is a flowchart provided by the present invention for determining a target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword.

[0024] Figure 6 It is a structural diagram of the house evaluation system provided by the present invention.

[0025] Figure 7 It is a structural diagram of the house search system provided by the present invention.

[0026] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0028] This invention provides a housing evaluation method designed to optimize the display of housing information. By integrating reviews from real estate agents and homeowners, it removes information irrelevant to buyers and precise information provided by the platform (such as the number of rooms and the orientation of the house), focusing on perceptual aspects such as lighting and sound insulation. In this way, customers can experience what it will be like to move in before they even move in, allowing them to more accurately select their preferred property. This method not only enhances the user experience but also increases the practicality and appeal of housing information, and has broad application prospects.

[0029] Figure 1 It is a flow chart of the house evaluation method provided by the present invention.

[0030] The following will be combined Figure 1 The process of the house evaluation method provided by the present invention is described.

[0031] In an exemplary embodiment of the present invention, Figure 1 It can be seen that the house evaluation method may include steps 110 to 130, and each step will be introduced below.

[0032] In step 110 , the perceptual description information of the house to be evaluated is collected, wherein the perceptual description information is used to describe the user experience of the house to be evaluated.

[0033] In one embodiment, perceptual description information can be collected for the property to be reviewed. This perceptual description information can be used to describe the user experience of the property to be reviewed. Examples include real estate agent reviews, homeowner recommendations, and information about the neighborhood. By acquiring multiple sets of perceptual description information from different perspectives, the final perceptual review of the property to be reviewed can be comprehensive and accurate.

[0034] In step 120, a cleaning process is performed based on the sensitivity description information to obtain target sensitivity description information, wherein the target sensitivity description information is the information obtained by performing a cleaning process on the sensitivity description information to remove duplicates and / or invalid information.

[0035] In another embodiment, the sensitivity description information can be cleaned to obtain target sensitivity description information. In yet another example, the large model can be used to remove duplicate and invalid information from the sensitivity description information to obtain target sensitivity description information. The target sensitivity description information is the sensitivity description information cleaned to remove duplicate and invalid information. It is understood that the target sensitivity description information is a valid description of the user experience of the property to be evaluated.

[0036] It should be noted that cleaning processing refers to the process of removing invalid information from the original perception description information. For example, the original perception description information is "that, this, the sunlight in the house is good", where the invalid information can be invalid words such as "that, this," and the information after cleaning can be "The sunlight in the house is good".

[0037] In step 130 , the house to be evaluated is evaluated based on the target sensitivity description information to obtain various sensitivity evaluation texts of the house to be evaluated, wherein the sensitivity evaluation text is a text that describes the evaluation from the dimension of usage experience.

[0038] In another embodiment, the target house can be evaluated based on the target sensitivity description information, thereby obtaining individual sensitivity evaluation texts for the house. In one example, the target sensitivity description information can be summarized into a descriptive sentence to serve as the sensitivity evaluation text for the house. Continuing with the previously described cleaned information, where the target sensitivity description information is "The house has good sunlight," a sensitivity evaluation text for the house can be obtained based on this target sensitivity description information, such as "The house has good lighting conditions."

[0039] In this embodiment, since the sensory evaluation text is a text that describes the evaluation from the dimension of usage experience, it is possible to fully describe the subjective feeling description of the house, thereby ensuring that customers can obtain the experience after moving in before moving in, and can more accurately match suitable houses.

[0040] In another exemplary embodiment of the present invention, continuing with the above Figure 1 The embodiment described above is used as an example for explanation, wherein the receptive description information of the house to be evaluated (corresponding to step 110) can be obtained in the following manner: Obtaining objective attribute description information of the house to be evaluated, wherein the objective attribute description information is used to describe the objective physical attributes of the house to be evaluated; Based on the objective attribute description information of the house to be evaluated, the perceptual description information of the house to be evaluated that matches the objective attribute description information is obtained.

[0041] In one embodiment, objective attribute description information of the house to be evaluated can be obtained, where the objective attribute description information is used to describe the objective physical attributes of the house to be evaluated. Because the subjective experience of a house is ultimately determined by the objective physical attributes of the house, and there is a correlation between the two, based on the objective attribute description information of the house to be evaluated, perceptual description information of the house to be evaluated that matches the objective attribute description information can be obtained.

[0042] In another embodiment, a pre-trained language model can be used to input the objective attribute description information of the house to be evaluated into the language model, thereby obtaining the perceptual description information of the house to be evaluated that matches the objective attribute description information. This embodiment allows for convenient and accurate acquisition of the perceptual description information of the house to be evaluated, wherein the language model can determine the perceptual description information that matches the objective attribute description information based on the objective attribute description information of the house to be evaluated.

[0043] In another exemplary embodiment of the present invention, continuing with the above Figure 1 The embodiment described above is used as an example for explanation, wherein the receptive description information of the house to be evaluated (corresponding to step 110) can be obtained in the following manner: Obtain the initial perception description information of different role users towards the evaluated house; Determine the evaluation weight of each role user based on the degree of association between different role users and the house to be evaluated; Based on the evaluation weights of the users of various roles and the initial sensitivity description information of the house to be evaluated by the users of various roles, weighted processing is performed to obtain the sensitivity description information of the house to be evaluated.

[0044] In one embodiment, the perception description information of the house to be reviewed from different perspectives can be obtained. For example, the initial perception description information of the house to be reviewed by different role users can be obtained. The different role users can include at least the role users such as the agent, the homeowner, and the tenant.

[0045] Furthermore, based on the degree of association between different role users and the house to be evaluated, evaluation weights for each role user are determined. Based on these evaluation weights and each role user's initial perceptual description of the house to be evaluated, a weighted process is performed to comprehensively determine perceptual description information for the house to be evaluated. The degree of association between different role users and the house to be evaluated can be the frequency and / or duration of residence of each role user in the house to be evaluated. In this embodiment, by determining the final perceptual description information for the house to be evaluated based on the initial perceptual description information of the house to be evaluated by different role users, the comprehensiveness and accuracy of the perceptual description information can be improved, laying the foundation for subsequent comprehensive characterization of the subjective perceptual description of the house based on the perceptual description information.

[0046] The present invention also provides a housing search method. Figure 2 This is a flow chart of the house search method provided by the present invention. Figure 2 The process of the house search method provided by the present invention is described.

[0047] In an exemplary embodiment of the present invention, Figure 2 It can be seen that the housing search method may include steps 210 to 220, and each step will be introduced below.

[0048] In step 210, the user's house search information is obtained, wherein the house search information is search information under the experience dimension.

[0049] In step 220 , based on the house search information and the various receptive evaluation texts about the various houses, a target house matching the house search information is screened out from a plurality of houses.

[0050] In one embodiment, house search information sent by a user can be obtained, wherein the house search information can be understood as the user's experience description information used to search for a favorite house. The house search information is search information under the experience dimension. Furthermore, by comparing the house search information with the various perceptual evaluation texts about each house, a target house that matches the house search information can be screened out from multiple houses, thereby enabling the user to be more accurately matched to a suitable house in terms of experience. It should be noted that the various perceptual evaluation texts of each house in this embodiment can be determined according to the house evaluation method described in any of the previous embodiments. It can be understood that the house in this embodiment can correspond to the house to be evaluated in the house evaluation method.

[0051] Figure 3 This is one of the flowcharts provided by the present invention for screening a target house matching the house search information from a plurality of houses based on the house search information and the various perception evaluation texts about the houses.

[0052] The following will be combined Figure 3 The following describes a process of selecting a target house that matches the house search information from a plurality of houses based on the house search information and the various sensitivity evaluation texts about the houses.

[0053] In an exemplary embodiment of the present invention, the sensitivity evaluation text may be a sensitivity evaluation text sentence; Figure 3 It can be seen that based on the house search information and the various perception evaluation texts about the various houses, screening out a target house matching the house search information from the multiple houses may include steps 310 to 350, each of which will be described below.

[0054] In step 310 , based on the housing search information, a first text vector corresponding to the housing search information is determined.

[0055] In step 320 , based on the respective sensitivity evaluation text sentences, respective second text vectors corresponding to the respective sensitivity evaluation text sentences are determined.

[0056] In one embodiment, a first text vector corresponding to the housing search information can be determined based on the housing search information. Furthermore, second text vectors corresponding to the respective sentiment evaluation text sentences can be determined based on the respective sentiment evaluation text sentences. It is understood that the description of each housing item can be represented by each second text vector.

[0057] In step 330 , vector distances between the first text vector and each second text vector are calculated respectively.

[0058] In step 340 , the sensitivity evaluation text sentence corresponding to the minimum vector distance is used as the target sensitivity evaluation text sentence.

[0059] In step 350 , the house corresponding to the target sensitivity evaluation text sentence is used as the target house that matches the house search information.

[0060] In another embodiment, the vector distances between the first text vector and each second text vector can be calculated separately to obtain multiple sets of vector distances. It can be understood that the smaller the vector distance, the closer the first text vector and each second text vector are, that is, the more the corresponding house meets the user's search needs. Therefore, the sensitivity evaluation text sentence corresponding to the minimum vector distance can be used as the target sensitivity evaluation text sentence. Furthermore, the house corresponding to the target sensitivity evaluation text sentence is used as the target house that matches the house search information. Through this embodiment, a suitable house can be accurately matched for the user.

[0061] It should be noted that this embodiment determines the target house that matches the house search information by comparing the first text vector of the house search information and the second text vectors corresponding to the various perception evaluation text sentences. In one scenario, the house search information can be input through voice, and the corresponding first text vector can be obtained by parsing the voice. Then, based on the comparison between the first text vector and the second text vectors, the target house that matches the house search information is determined, thereby further improving the user experience and satisfaction.

[0062] Figure 4 This is the second flow chart of the present invention for screening a target house matching the house search information from a plurality of houses based on the house search information and the perceptual evaluation texts about the houses.

[0063] The following will be combined Figure 4 Another process of screening a plurality of houses to obtain a target house that matches the house search information based on the house search information and the various sensitivity evaluation texts about the various houses will be described.

[0064] In an exemplary embodiment of the present invention, the sensitivity evaluation text may be a sensitivity evaluation text keyword. Figure 4 It can be seen that based on the house search information and the various perception evaluation texts about the houses, screening a plurality of houses to obtain a target house that matches the house search information may include steps 410 to 430, each of which will be described below.

[0065] In step 410 , based on the housing search information, a search key matching the housing search information is determined.

[0066] In step 420 , based on the similarity between the search keyword and each sensitivity evaluation text keyword, a target sensitivity evaluation text keyword having the highest similarity to the search keyword is determined.

[0067] In step 430 , the house corresponding to the target sensitivity evaluation text keyword is used as the target house that matches the house search information.

[0068] In one embodiment, when the receptive evaluation text is a receptive evaluation text keyword, a search keyword matching the housing search information is determined based on the housing search information. Then, based on the similarity between the search keyword and each receptive evaluation text keyword, a target receptive evaluation text keyword with the highest similarity to the search keyword is determined. Furthermore, the housing corresponding to the target receptive evaluation text keyword is selected as the target housing matching the housing search information. This embodiment allows for rapid and accurate screening of target housing, ensuring that users are matched with suitable housing.

[0069] Figure 5 It is a flowchart provided by the present invention for determining a target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword.

[0070] The following will be combined Figure 5 The process of determining the target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword will be described.

[0071] In an exemplary embodiment of the present invention, each sensitivity evaluation text may include multiple sensitivity evaluation text keywords. Figure 5 It can be seen that based on the similarity between the search keyword and each of the sensitivity evaluation text keywords, determining the target sensitivity evaluation text keyword with the highest similarity to the search keyword can include steps 510 to 540, and each step will be introduced below.

[0072] In step 510 , clustering is performed on the plurality of sensitivity evaluation text keywords to obtain sensitivity evaluation text keywords under each cluster.

[0073] In step 520, based on the number of sensitivity evaluation text keywords under each cluster, the level of each cluster is determined, and cluster keywords are set for clusters of each level, wherein the number of sensitivity evaluation text keywords under the cluster is positively correlated with the level of the cluster; the cluster keywords are determined based on the sensitivity evaluation text keywords under the cluster.

[0074] In one embodiment, when each sensitivity evaluation text includes multiple sensitivity evaluation text keywords, the multiple sensitivity evaluation text keywords can be clustered to obtain sensitivity evaluation text keywords within each cluster. Clustering can be considered as clustering sensitivity evaluation text keywords with the same meaning together to obtain clusters. It is understood that sensitivity evaluation text keywords with the same meaning can be considered as sensitivity evaluation text keywords within a cluster.

[0075] Furthermore, based on the number of perceptual evaluation text keywords within each cluster, the rank of each cluster is determined, and cluster keywords are assigned to each rank. It is understood that a single property may include cluster keywords of varying ranks. The highest-ranked cluster keywords can be considered keywords that are more relevant to the subjective experience of the property. The number of perceptual evaluation text keywords within a cluster is positively correlated with the rank of the cluster; cluster keywords are determined based on the perceptual evaluation text keywords within the cluster.

[0076] In step 530 , based on the similarity between the search keyword and the cluster keywords of each highest-level cluster, a target cluster keyword having the highest similarity to the search keyword is determined.

[0077] In step 540 , the target cluster keyword is used as the target sensitivity evaluation text keyword having the highest similarity to the search keyword.

[0078] In another embodiment, since the highest-ranked cluster keywords can be considered keywords that are more relevant to the subjective experience of a property, the target cluster keywords with the highest similarity to the search keyword can be determined based on the similarity between the search keyword and the cluster keywords of each highest-ranked cluster. Furthermore, the target cluster keywords are used as the target perception evaluation text keywords with the highest similarity to the search keyword. Furthermore, the properties corresponding to the target perception evaluation text keywords can be selected as target properties that match the property search information.

[0079] The house evaluation system provided by the present invention is described below. The house evaluation system described below and the house evaluation method described above can be referenced to each other.

[0080] Figure 6 It is a structural diagram of the house evaluation system provided by the present invention.

[0081] The following will be combined Figure 6 The structure of the house evaluation system provided by the present invention is described.

[0082] In an exemplary embodiment of the present invention, Figure 6 It can be seen that the house evaluation system may include a collection module 610, a processing module 620, and an evaluation module 630. Each module will be introduced below.

[0083] The collection module 610 may be configured to collect user experience information of the house to be evaluated, wherein the user experience information is used to describe the user experience of the house to be evaluated. The processing module 620 may be configured to perform a cleaning process based on the receptivity description information to obtain target receptivity description information, wherein the target receptivity description information is the receptivity description information cleaned by removing duplicates and / or invalid information; The evaluation module 630 may be configured to evaluate the house to be evaluated based on the target sensitivity description information to obtain a sensitivity evaluation text of the house to be evaluated, wherein the sensitivity evaluation text is a text that describes the evaluation from the perspective of usage experience.

[0084] In an exemplary embodiment of the present invention, the acquisition module 610 may acquire the receptive description information of the house to be evaluated in the following manner: Obtaining objective attribute description information of the house to be evaluated, wherein the objective attribute description information is used to describe the objective physical attributes of the house to be evaluated; Based on the objective attribute description information of the house to be evaluated, the perceptual description information of the house to be evaluated that matches the objective attribute description information is obtained.

[0085] In an exemplary embodiment of the present invention, the acquisition module 610 may acquire the receptive description information of the house to be evaluated in the following manner: Obtaining initial perception description information of the house to be evaluated by users of different roles respectively; Determining the evaluation weight of each role user based on the degree of association between the different role users and the house to be evaluated; Based on the evaluation weights of the users of various roles and the weighted processing of the initial sensitivity description information of the house to be evaluated by the users of various roles, the sensitivity description information of the house to be evaluated is obtained.

[0086] Figure 7It is a structural diagram of the house search system provided by the present invention.

[0087] The following will be combined Figure 7 The structure of the housing search system is described.

[0088] In an exemplary embodiment of the present invention, Figure 7 As can be seen, the housing search system may include an acquisition module 710 and a search module 720. Each module will be described below: The acquisition module 710 may be configured to acquire housing search information of the user, wherein the housing search information is search information under the experience dimension; The search module 720 can be configured to screen a target house that matches the house search information from a plurality of houses based on the house search information and the various sentiment evaluation texts about the various houses, wherein the various sentiment evaluation texts about the various houses are determined using the house evaluation method described in any of the foregoing embodiments.

[0089] In an exemplary embodiment of the present invention, the sensitivity evaluation text is a sensitivity evaluation text sentence; The search module 720 may select a target house matching the house search information from among multiple houses based on the house search information and the perceptual evaluation texts of the houses in the following manner: Based on the housing search information, determining a first text vector corresponding to the housing search information; Based on each of the sensitivity evaluation text sentences, determining each second text vector corresponding to each of the sensitivity evaluation text sentences; respectively calculating respective vector distances between the first text vector and respective second text vectors; The sensitivity evaluation text sentence corresponding to the minimum vector distance is used as the target sensitivity evaluation text sentence; The house corresponding to the target sensitivity evaluation text sentence is used as a target house that matches the house search information.

[0090] In an exemplary embodiment of the present invention, the sensitivity evaluation text is sensitivity evaluation text keywords; The search module 720 may select a target house matching the house search information from among multiple houses based on the house search information and the perceptual evaluation texts of the houses in the following manner: Determining, based on the housing search information, a search keyword that matches the housing search information; Based on the similarity between the search keyword and each of the sensitivity evaluation text keywords, determining a target sensitivity evaluation text keyword having the highest similarity to the search keyword; The house corresponding to the target sensitivity evaluation text keyword is used as the target house matching the house search information.

[0091] In an exemplary embodiment of the present invention, each of the sensitivity evaluation texts includes a plurality of sensitivity evaluation text keywords; The search module 720 may determine the target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword in the following manner: performing clustering processing on the plurality of sensitivity evaluation text keywords to obtain sensitivity evaluation text keywords under each cluster; Determining the level of each cluster based on the number of sentiment evaluation text keywords under each cluster, and setting cluster keywords for each cluster of each level, wherein the number of sentiment evaluation text keywords under the cluster is positively correlated with the level of the cluster; and the cluster keywords are determined based on the sentiment evaluation text keywords under the cluster; Based on the similarity between the search keyword and the cluster keywords of each highest-level cluster, determining a target cluster keyword having the highest similarity to the search keyword; The target cluster keyword is used as the target sensitivity evaluation text keyword having the highest similarity to the search keyword.

[0092] Figure 8 An example of a physical structure diagram of an electronic device is shown below. Figure 8As shown, the electronic device may include: a processor 810 , a communication interface 820 , a memory 830 and a communication bus 840 , wherein the processor 810 , the communication interface 820 and the memory 830 communicate with each other via the communication bus 840 . The processor 810 can call logic instructions in the memory 830 to execute a house evaluation method, the method including: collecting perceptual description information of a house to be evaluated, wherein the perceptual description information is used to describe the user experience of the house to be evaluated; performing cleaning processing based on the perceptual description information to obtain target perceptual description information, wherein the target perceptual description information is information obtained by cleaning the perceptual description information to remove duplicates and / or invalid information; evaluating the house to be evaluated based on the target perceptual description information to obtain a perceptual evaluation text of the house to be evaluated, wherein the perceptual evaluation text is a text that evaluates the house to be evaluated from the dimension of user experience; or performing a house search method, the method including: obtaining house search information from a user, wherein the house search information is search information from the dimension of user experience; based on the house search information and each perceptual evaluation text about each house to be evaluated, screening a target house to be evaluated from a plurality of houses to be evaluated to obtain the target house to be evaluated that matches the house search information, wherein each perceptual evaluation text of each house to be evaluated is determined using any one of the house evaluation methods described above.

[0093] Furthermore, the logic instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0094] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the house evaluation method provided by the above methods, which method includes: collecting sensory description information of the house to be evaluated, wherein the sensory description information is used to describe the user experience of the house to be evaluated; performing cleaning processing based on the sensory description information to obtain target sensory description information, wherein the target sensory description information is the information obtained by cleaning the sensory description information to remove duplicates and\or remove invalid information; according to the The target sensitivity description information is used to evaluate the house to be evaluated to obtain a sensitivity evaluation text of the house to be evaluated, wherein the sensitivity evaluation text is a text that describes the evaluation from the dimension of usage experience; or a house search method is performed, which includes: obtaining house search information of the user, wherein the house search information is search information under the dimension of experience; based on the house search information and each sensitivity evaluation text about each house to be evaluated, screening a plurality of houses to be evaluated to obtain a target house to be evaluated that matches the house search information, wherein each sensitivity evaluation text of each house to be evaluated is determined by using any one of the house evaluation methods.

[0095] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the housing evaluation method provided by the above-mentioned methods, the method comprising: collecting perceptual description information of the housing to be evaluated, wherein the perceptual description information is used to describe the user experience of the housing to be evaluated; performing cleaning processing based on the perceptual description information to obtain target perceptual description information, wherein the target perceptual description information is the information obtained by performing cleaning processing on the perceptual description information to remove duplicates and\or invalid information; and evaluating the housing according to the target perceptual description information. Evaluate the house to be evaluated and obtain a perceptual evaluation text of the house to be evaluated, wherein the perceptual evaluation text is a text that describes the evaluation from the dimension of usage experience; or perform a house search method, the method comprising: obtaining house search information of the user, wherein the house search information is search information under the dimension of usage experience; based on the house search information and each perceptual evaluation text about each house to be evaluated, screen out a target house to be evaluated that matches the house search information from a plurality of houses to be evaluated, wherein each perceptual evaluation text of each house to be evaluated is determined using any one of the house evaluation methods.

[0096] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0097] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A housing evaluation method, characterized in that: The method comprises: Collecting perceptual description information of the house to be evaluated, wherein the perceptual description information is used to describe the user experience of the house to be evaluated; performing a cleaning process based on the receptivity description information to obtain target receptivity description information, wherein the target receptivity description information is the receptivity description information cleaned by removing duplicates and / or invalid information; The house to be evaluated is evaluated according to the target sensitivity description information to obtain a sensitivity evaluation text of the house to be evaluated, wherein the sensitivity evaluation text is a text that describes the evaluation from the dimension of usage experience.

2. The housing evaluation method according to claim 1, wherein: The receptive description information of the house to be evaluated is obtained in the following way: Obtaining objective attribute description information of the house to be evaluated, wherein the objective attribute description information is used to describe the objective physical attributes of the house to be evaluated; Based on the objective attribute description information of the house to be evaluated, the perceptual description information of the house to be evaluated that matches the objective attribute description information is obtained.

3. The housing evaluation method according to claim 1, wherein: The receptive description information of the house to be evaluated is obtained in the following way: Obtaining initial perception description information of the house to be evaluated by users of different roles respectively; Determining the evaluation weight of each role user based on the degree of association between the different role users and the house to be evaluated; Based on the evaluation weights of the users of various roles and the weighted processing of the initial sensitivity description information of the house to be evaluated by the users of various roles, the sensitivity description information of the house to be evaluated is obtained.

4. A housing search method, characterized in that: The method comprises: Acquiring housing search information of the user, wherein the housing search information is search information under the dimension of experience and feeling; Based on the house search information and the various sensitivity evaluation texts about each house, a target house matching the house search information is screened out from a plurality of the houses, wherein the various sensitivity evaluation texts about each house are determined using the house evaluation method described in any one of claims 1 to 3.

5. The housing search method according to claim 4, characterized in that: The receptivity evaluation text is a receptivity evaluation text sentence; The step of screening a target house matching the house search information from a plurality of houses based on the house search information and the respective receptive evaluation texts about the respective houses specifically includes: Based on the housing search information, determining a first text vector corresponding to the housing search information; Based on each of the sensitivity evaluation text sentences, determining each second text vector corresponding to each of the sensitivity evaluation text sentences; respectively calculating respective vector distances between the first text vector and respective second text vectors; The sensitivity evaluation text sentence corresponding to the minimum vector distance is used as the target sensitivity evaluation text sentence; The house corresponding to the target sensitivity evaluation text sentence is used as a target house that matches the house search information.

6. The housing search method according to claim 4, characterized in that: The receptivity evaluation text is a receptivity evaluation text keyword; The step of screening a target house matching the house search information from a plurality of houses based on the house search information and the respective receptive evaluation texts about the respective houses specifically includes: Based on the housing search information, determining a search keyword that matches the housing search information; Based on the similarity between the search keyword and each of the sensitivity evaluation text keywords, determining a target sensitivity evaluation text keyword having the highest similarity to the search keyword; The house corresponding to the target sensitivity evaluation text keyword is used as the target house matching the house search information.

7. The housing search method according to claim 6, characterized in that: Each of the sensitivity evaluation texts includes a plurality of sensitivity evaluation text keywords; The determining of the target sensitivity evaluation text keyword having the highest similarity to the search keyword based on the similarity between the search keyword and each sensitivity evaluation text keyword specifically includes: performing clustering processing on the plurality of sensitivity evaluation text keywords to obtain sensitivity evaluation text keywords under each cluster; Determining the level of each cluster based on the number of sentiment evaluation text keywords under each cluster, and setting cluster keywords for each cluster of each level, wherein the number of sentiment evaluation text keywords under the cluster is positively correlated with the level of the cluster; and the cluster keywords are determined based on the sentiment evaluation text keywords under the cluster; Based on the similarity between the search keyword and the cluster keywords of each highest-level cluster, determining a target cluster keyword having the highest similarity to the search keyword; The target cluster keyword is used as the target sensitivity evaluation text keyword having the highest similarity to the search keyword.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the house evaluation method according to any one of claims 1 to 3 and the house search method according to any one of claims 4 to 7 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the house evaluation method according to any one of claims 1 to 3 and the house search method according to any one of claims 4 to 7 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the house evaluation method according to any one of claims 1 to 3 and the house search method according to any one of claims 4 to 7 are implemented.

Images