CN111340527B - House assessment method, house assessment device, computer readable storage medium and electronic equipment - Google Patents
House assessment method, house assessment device, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111340527B CN111340527B CN202010089786.4A CN202010089786A CN111340527B CN 111340527 B CN111340527 B CN 111340527B CN 202010089786 A CN202010089786 A CN 202010089786A CN 111340527 B CN111340527 B CN 111340527B
- Authority
- CN
- China
- Prior art keywords
- house
- evaluation
- sample
- houses
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000011156 evaluation Methods 0.000 claims abstract description 221
- 238000013210 evaluation model Methods 0.000 claims abstract description 133
- 238000012216 screening Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013507 mapping Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/167—Closing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure discloses a house evaluation method, a house evaluation device, a computer-readable storage medium and electronic equipment. The method comprises the following steps: analyzing the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses; according to the analysis result, screening a sample house referenced when evaluating the evaluating house by a house evaluating model from a plurality of sample houses; and outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house. Therefore, compared with the prior art, the embodiment of the disclosure can improve the convincing power of the evaluation result.
Description
Technical Field
The disclosure relates to the technical field of information processing, and in particular relates to a house evaluation method, a house evaluation device, a computer readable storage medium and electronic equipment.
Background
In some cases, house evaluations may be performed using house evaluation models, such as evaluating house prices. In general, the house evaluation model directly outputs the evaluation result of the house, however, it is not clear to the user how the evaluation result is obtained, and therefore, the evaluation result of the house evaluation model is not convinced to the user.
Disclosure of Invention
The present disclosure has been made in order to solve the above technical problems. Embodiments of the present disclosure provide a house evaluation method, apparatus, computer-readable storage medium, and electronic device.
According to an aspect of an embodiment of the present disclosure, there is provided a house evaluation method including:
analyzing the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses;
screening sample houses referenced when the house evaluation model evaluates the evaluation house from the plurality of sample houses according to the analysis result;
and outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house.
In an alternative example, the house evaluation model includes a plurality of trees, and the analysis result includes structural information of each tree in the plurality of trees;
and screening sample houses referenced by the house evaluation model when evaluating the evaluation house from the plurality of sample houses according to the analysis result, wherein the sample houses comprise:
determining a path of each sample house in the plurality of sample houses on each tree according to the structure information in the analysis result, and evaluating the path of the house on each tree;
and screening sample houses referenced by the house evaluation model when evaluating the evaluation houses from the plurality of sample houses according to the path of each sample house on each tree and the path of the evaluation house on each tree.
In an alternative example, the filtering, from the plurality of sample houses, the sample houses referred to when the house evaluation model evaluates the evaluation house according to the path of each sample house on each tree and the path of the evaluation house on each tree includes:
determining a sample house consistent with the path of the evaluation house on at least one tree in the plurality of sample houses according to the path of each sample house on each tree and the path of the evaluation house on each tree;
And taking the determined sample house as a sample house which is referred when the house evaluation model evaluates the evaluation house.
In an optional example, the outputting, according to the screened sample house, interpretation information of the evaluation result of the house evaluation model on the evaluation house includes:
determining sample houses meeting preset conditions in the screened sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the determined sample house;
and outputting the interpretation information.
In one example of an alternative implementation of the method,
the determining the sample house meeting the preset condition in the screened sample houses comprises the following steps:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
the generating, according to the determined sample house, interpretation information of the house evaluation model on the evaluation result of the evaluation house includes:
obtaining average price and total number of the sample houses in the determined sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; wherein the interpretation information comprises the obtained mapping relation of average price and total quantity.
In one example of an alternative implementation of the method,
the determining the sample house meeting the preset condition in the screened sample houses comprises the following steps:
determining a sample house with a house state being a preset state in the screened sample houses;
the generating, according to the determined sample house, interpretation information of the house evaluation model on the evaluation result of the evaluation house includes:
acquiring target information of at least one sample house in the determined sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; the interpretation information comprises the target information, wherein the target information comprises house basic information and deal information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
In an optional example, the outputting, according to the screened sample house, interpretation information of the evaluation result of the house evaluation model on the evaluation house includes:
obtaining average price and total number of sample houses in the screened sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; wherein the interpretation information comprises the obtained mapping relation between average price and total quantity;
And outputting the interpretation information.
According to another aspect of an embodiment of the present disclosure, there is provided a house evaluation device including:
the analysis module is used for analyzing the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses;
the screening module is used for screening sample houses referenced when the house evaluation model evaluates the evaluation houses from the plurality of sample houses according to the analysis result;
and the output module is used for outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house.
In an alternative example, the house evaluation model includes a plurality of trees, and the analysis result includes structural information of each tree in the plurality of trees;
the screening module comprises:
a first determining unit configured to determine a path of each of the plurality of sample houses on each tree, and a path of the evaluation house on each tree, based on the structure information in the analysis result;
a screening unit for screening, from the plurality of sample houses, a sample house to which the house evaluation model refers when evaluating the evaluation house, based on a path of each sample house on each tree and a path of the evaluation house on each tree.
In an alternative example, the screening unit includes:
a first determining subunit configured to determine, from the path of each sample house on each tree and the path of the evaluation house on each tree, a sample house, among the plurality of sample houses, that is consistent with the path of the evaluation house on at least one tree;
and a second determination subunit configured to use the determined sample house as a sample house referred to when the house evaluation model evaluates the evaluation house.
In an alternative example, the output module includes:
a second determining unit configured to determine sample houses satisfying a preset condition among the screened sample houses;
a first generation unit configured to generate interpretation information of an evaluation result of the evaluation house by the house evaluation model, based on the determined sample house;
and a first output unit for outputting the interpretation information.
In one example of an alternative implementation of the method,
the second determining unit is specifically configured to:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
the first generation unit includes:
a first acquisition subunit for acquiring the determined average price and total number of sample houses in the sample houses;
A first generation subunit for generating interpretation information of the evaluation result of the house evaluation by the house evaluation model; wherein the interpretation information comprises the obtained mapping relation of average price and total quantity.
In one example of an alternative implementation of the method,
the second determining unit is specifically configured to:
determining a sample house with a house state being a preset state in the screened sample houses;
the first generation unit includes:
a second acquisition subunit configured to acquire target information of at least one of the determined sample houses;
a second generation subunit, configured to generate interpretation information of the evaluation result of the evaluation house by the house evaluation model; the interpretation information comprises the target information, wherein the target information comprises house basic information and deal information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
In an alternative example, the output module includes:
an acquisition unit for acquiring average prices and total numbers of sample houses among the screened sample houses;
A second generation unit configured to generate interpretation information of an evaluation result of the evaluation house by the house evaluation model; wherein the interpretation information comprises the obtained mapping relation between average price and total quantity;
and a second output unit for outputting the interpretation information.
According to still another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above house evaluation method.
According to still another aspect of the embodiments of the present disclosure, there is provided an electronic device including:
a processor;
a memory for storing the processor-executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize the house evaluation method.
In the embodiment of the disclosure, after a house evaluation model obtained by training house data of a plurality of sample houses is parsed to obtain a parsing result, a sample house referred to when the house evaluation model evaluates the evaluation house is screened from the plurality of sample houses according to the parsing result, and then interpretation information of the house evaluation model on the evaluation result of the evaluation house can be output according to the screened sample house. Therefore, compared with the prior art, the embodiment of the disclosure can improve the convincing power of the evaluation result.
The technical scheme of the present disclosure is described in further detail below through the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing embodiments thereof in more detail with reference to the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, without limitation to the disclosure. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a flow chart of a house evaluation method according to an exemplary embodiment of the present disclosure.
Fig. 2 is a schematic diagram of the use of the model.
Fig. 3 is a flow chart of a house evaluation method provided in another exemplary embodiment of the present disclosure.
FIG. 4 is a schematic diagram of a tree in a house assessment model.
Fig. 5 is a schematic diagram of a general model interpretation method.
Fig. 6 is an output schematic diagram explaining information.
Fig. 7 is a schematic structural view of a house evaluation device provided in an exemplary embodiment of the present disclosure.
Fig. 8 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.
Detailed Description
Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present disclosure and not all of the embodiments of the present disclosure, and that the present disclosure is not limited by the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.
It will be appreciated by those of skill in the art that the terms "first," "second," etc. in embodiments of the present disclosure are used merely to distinguish between different steps, devices or modules, etc., and do not represent any particular technical meaning nor necessarily logical order between them.
It should also be understood that in embodiments of the present disclosure, "plurality" may refer to two or more, and "at least one" may refer to one, two or more.
It should also be appreciated that any component, data, or structure referred to in the presently disclosed embodiments may be generally understood as one or more without explicit limitation or the contrary in the context.
In addition, the term "and/or" in this disclosure is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the front and rear association objects are an or relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and that the same or similar features may be referred to each other, and for brevity, will not be described in detail.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Embodiments of the present disclosure may be applicable to electronic devices such as terminal devices, computer systems, servers, etc., which may operate with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with the terminal device, computer system, server, or other electronic device include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments that include any of the above systems, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment in which tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computing system storage media including memory storage devices.
Exemplary method
Fig. 1 is a flow chart of a house evaluation method according to an exemplary embodiment of the present disclosure. The method shown in fig. 1 includes step 101, step 102 and step 103, and each step is described below.
Here, the purpose of the house evaluation model may be to evaluate a house, and in this case, the house evaluation model may also be referred to as a house evaluation model; the type of house assessment model may be a tree-model based extreme gradient lifting (eXtreme Gradient Boosting, XGBoost) model. Of course, the use and type of the house evaluation model are not limited thereto, and may be specifically determined according to actual situations, and are not listed here.
Here, the house evaluation model can be trained according to house data of 5000, 6000, 8000, 10000 or other number of sample houses; the house data may include house base information and house prices, among others, including, but not limited to, house area, house apartment, house floor, house orientation, house age, the cell to which the house belongs, greening of the cell to which the house belongs, and the like.
Generally, as shown in fig. 2, the model obtained through data training is a black box for the user, and in the embodiment of the disclosure, the house evaluation model can be changed into a white box for the user through analyzing the house evaluation model to obtain an analysis result; the analysis result may be information that can be recognized and stored by the machine.
And 102, screening sample houses referenced by a house evaluation model when evaluating the evaluation houses from a plurality of sample houses according to the analysis result.
Here, the evaluation house may be any house that needs to be evaluated, for example, any house that needs to be evaluated.
Since the house evaluation model is obtained by training house data of a plurality of sample houses, when evaluating the house by using the house evaluation model, the evaluation process must refer to a part of sample houses in the plurality of sample houses, and then in step 102, the referenced sample houses may be screened according to the analysis result obtained in step 101.
Here, the total number of sample houses among the sample houses screened may be 50, 100, 150, 200, 300, etc., which are not listed here.
And step 103, outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house.
Here, house basic information (i.e., house area, house type, etc.) of the evaluation house may be input into the house evaluation model to obtain an evaluation result (e.g., house valuation) of the evaluation house output from the house evaluation model. In addition, according to the sample houses screened in step 102, interpretation information of the evaluation result may be generated, where the interpretation information is used to interpret the evaluation result. After that, the interpretation information may be outputted in the form of voice play, screen display, mail transmission, etc., so that the user can view the interpretation information.
In the embodiment of the disclosure, after a house evaluation model obtained by training house data of a plurality of sample houses is parsed to obtain a parsing result, a sample house referred to when the house evaluation model evaluates the evaluation house is screened from the plurality of sample houses according to the parsing result, and then interpretation information of the house evaluation model on the evaluation result of the evaluation house can be output according to the screened sample house. Therefore, compared with the prior art, the embodiment of the disclosure can improve the convincing power of the evaluation result.
Fig. 3 is a flow chart of a house evaluation method provided in another exemplary embodiment of the present disclosure. The method shown in fig. 3 includes step 301, step 302, step 303, and step 304, and each step is described below.
Here, the house evaluation model may be an XGBoost model based on a tree model, and in this case, the house evaluation model may be a structure composed of a plurality of trees.
Specifically, one tree of the plurality of trees may be as shown in fig. 4, and each circle in fig. 4 represents a node; wherein the nodes of the first two rows are intermediate nodes, and the nodes of the last row are leaf nodes.
Generally, the data needs to be partitioned according to the feature and the feature value in the intermediate node when the data is at the intermediate node, for example, if the feature value of the feature is less than 98.8950043 or is missing at the intermediate node of the first row, the data is partitioned to the intermediate node of the second row on the left, otherwise, the data is partitioned to the intermediate node of the second row on the right. The subsequent segmentation process is performed sequentially until the lowest leaf node, each with a score as an output value (e.g., 0.00231639738, 0.00617906637, etc. in fig. 4).
It can be easily seen that a large amount of information is presented in fig. 4, including:
(1) The tree in fig. 4 includes four paths, including three features, build_ size, dealdate _ftr_new and floor_ftr, including three feature values 98.8950043, 39.5, 15, and four scores 0.00231639738, 0, 0.00617906637, 0; wherein build_size may characterize building area, dealdate_ftr_new may characterize latest transaction time, floor_ftr may characterize ground characteristics;
(2) For any house, in the case that house base information of the house meets the condition that the building size is smaller than 98.8950043 or the building size is missing, and the dealdate_ftr_new is smaller than 39.5 or the dealdate_ftr_new is missing, the first path is taken on the tree; in the case that the house base information thereof satisfies that the build_size is smaller than 98.8950043 and the dealdate_ftr_new is not smaller than 39.5, the second path is taken on the tree; in the case that the house base information satisfies that the build_size is not less than 98.8950043 and floor_ftr is less than 15 or floor_ftr is missing, the house base information walks a third path on the tree; in the case that the house base information thereof satisfies that the build_size is not less than 98.8950043 and the floor_ftr is not less than 15, it walks a fourth path on the tree.
It should be noted that, the structural information of this tree in the parsing result may include all the information presented in fig. 4. The structural information of any tree can then be used to describe all paths on a tree, the features and feature values on the paths, the scores of the last leaf nodes, etc.
Of course, the types of the features are not limited to build_ size, dealdate _ftr_new and floor_ftr, and the features may also include a tile, a bld_ longitude, cubage _ratio, and the like, which are not listed here; where latitudes may characterize latitudes, longitudes may characterize longitudes, cubage_ratio may characterize volume ratios.
Because the analysis result includes the structure information of each tree, for any house, the path of the house on the tree corresponding to fig. 4 can be conveniently and reliably determined only by obtaining the characteristic values of build_ size, dealdate _ftr_new and floor_ftr in the basic information of the house. In this way, the path of each sample house in the plurality of sample houses on each tree, and the path of the evaluating house on each tree, can be determined; wherein each house has only one unique path on each tree.
It should be noted that, the specific implementation manner of step 303 is various, and is described below by way of example.
In one embodiment, step 303 comprises:
determining a sample house consistent with the path of the estimated house on at least one tree in the plurality of sample houses according to the path of each sample house on each tree and the path of the estimated house on each tree;
and taking the determined sample house as a sample house which is referred when evaluating the evaluating house by using the house evaluating model.
Assuming that the house evaluation model includes 100 trees, the path of the evaluation house on the 1 st tree is L1, the path of the evaluation house on the 2 nd tree is L2, … …, the path of the evaluation house on the 100 st tree is L100, then from all the sample houses, the sample house with the path of L1 on the 1 st tree, the sample house with the path of L2 on the 2 nd tree, … …, and the sample house with the path of L100 on the 100 st tree can be determined, and each sample house can be used as one of the sample houses referred to when evaluating the evaluation house by the house evaluation model.
It can be seen that in this embodiment, based on the consistency of the paths, it is very convenient to determine the sample house to which the house evaluation model refers when evaluating the evaluation house.
Of course, the specific embodiment of step 303 is not limited thereto, and it is also possible to determine, for example, a sample house that coincides with the path of the evaluation house on all trees from among all sample houses, or a sample house that coincides with the path of the evaluation house on a certain proportion of trees, and evaluate the evaluation house with the determined sample house as a house evaluation model.
And step 304, outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house.
Here, the specific implementation procedure of step 304 may be referred to the description of the specific implementation procedure of step 103, which is not repeated here.
It should be noted that, in the case where the house evaluation model includes a plurality of trees, the scores of the corresponding leaf nodes on all the trees may be summed up for evaluating the house to obtain a summation result, and the summation result may be obtained by using the following formula:
the summed result may then be used as an evaluation result of the house evaluation model for evaluating the house.
In the embodiment of the disclosure, after a house evaluation model obtained through training according to house data of a plurality of sample houses is parsed to obtain a parsing result, a path of each sample house in the plurality of sample houses on each tree and a path of an evaluation house on each tree are determined according to structural information in the parsing result, and according to the path of each sample house on each tree and the path of the evaluation house on each tree, the sample houses referenced when the evaluation house is evaluated by the house evaluation model are screened from the plurality of sample houses. And then, according to the screened sample houses, outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house. Therefore, in the embodiment of the disclosure, based on the structural information of each tree in the house evaluation model and the consistency of the paths, the sample house referenced when the house evaluation model evaluates the evaluation house can be conveniently and reliably screened, and the interpretation information of the house evaluation model on the evaluation result of the evaluation house is output according to the sample house, and the interpretation information can interpret the evaluation result to assist the user in understanding the origin of the evaluation result, so that compared with the prior art, the embodiment of the disclosure can improve the convincing ability of the evaluation result.
As shown in fig. 5, the currently used model interpretation methods are: sample weight method, sample polymerization method, feature importance method, model replacement method and result disturbance method. From the foregoing discussion, the model interpretation method of sampling in embodiments of the present disclosure is a sample aggregation method.
In an alternative example, according to the screened sample house, the interpretation information of the evaluation result of the house evaluation model on the evaluation house is output, including:
determining sample houses meeting preset conditions in the screened sample houses;
generating interpretation information of a house evaluation model on an evaluation result of the evaluation house according to the determined sample house;
and outputting the interpretation information.
It should be noted that, there are various possible implementation forms for determining a sample house satisfying a preset condition in the screened sample houses and generating interpretation information of an evaluation result of the evaluation house by the house evaluation model according to the determined sample houses, and the following is described by way of example.
In one form of implementation the method, in one implementation,
determining sample houses meeting preset conditions in the screened sample houses, wherein the method comprises the following steps:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
Generating interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the determined sample house, comprising:
obtaining average price and total number of the sample houses in the determined sample houses;
generating interpretation information of a house evaluation model on an evaluation result of evaluating the house; wherein, the interpretation information comprises the mapping relation of the obtained average price and the total number.
Here, the preset attributes include, but are not limited to, house type attributes, house floor attributes, house orientation attributes, house affiliated cell attributes, and the like.
After screening out the sample houses referenced when the house evaluation model evaluates the evaluation houses, each sample house in the screened sample houses can be obtained from a background server of the house enterprise, and information such as house types, house floors, house orientations, communities to which the houses belong and the like of the evaluation houses can be obtained. If the house type of a certain sample house is the same as or has high similarity with the house type of the estimated house, the attribute matching of the house type of the sample house and the estimated house can be determined; if the floor of a certain sample house is the same as that of the estimated house, determining that the property of the sample house is the same as that of the estimated house; if a sample house and an evaluation house are located in the same cell, it can be determined that the sample house and the evaluation house match with the attribute of the cell to which the evaluation house belongs.
It is easy to see that, through the mode, the sample houses with preset attributes matched with the evaluation houses in the screened sample houses can be conveniently determined. Thereafter, the total number of sample houses in the determined sample houses (which may be referred to as a first total number in the following for convenience of distinction) may be calculated, and the house price of each of the determined sample houses may be obtained from the background server in order to calculate the average price of the sample houses in the determined sample houses (which may be referred to as a first average price in the following for convenience of distinction). Further, interpretation information including the mapping relation of the first average price and the first total number may be generated, and the interpretation information may be output by means of voice playing, screen display, or the like.
Specifically, as shown in fig. 6, assuming that the preset attribute is a house type attribute, the interpretation information may include a mapping relationship of "same house 200 sets" (which corresponds to the first total number) and "1.82 ten thousand/six minutes" (which corresponds to the first average price). Assuming that the preset attributes include house type attributes and house orientation attributes, the interpretation information may include a mapping relationship of "same house same orientation 150 sets" (which corresponds to the first total number) and "2.12 ten thousand/parallel" (which corresponds to the first average price). Assuming that the preset attributes include the attribute of the affiliated cell, the attribute of the house type and the attribute of the house orientation, the interpretation information may include a mapping relationship of "100 sets of the same cell and the same house orientation" (which corresponds to the first total number) and "1.62 ten thousand/six hundred thousand/six thousand" (which corresponds to the first average price).
In the implementation form, the interpretation information can assist the user to quickly know the related information of the sample house referenced when the house evaluation model evaluates the evaluation house, so as to assist the user to understand the origin of the evaluation result, thereby ensuring the convincing of the evaluation result.
In a further form of implementation the method, in one implementation,
determining sample houses meeting preset conditions in the screened sample houses, wherein the method comprises the following steps:
determining a sample house with a house state being a preset state in the screened sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the determined sample house, comprising:
acquiring target information of at least one sample house in the determined sample houses;
generating interpretation information of a house evaluation model on an evaluation result of evaluating the house; the interpretation information comprises target information, wherein the target information comprises house basic information and achievement information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
After screening out the sample houses referenced when the house evaluation model evaluates the evaluation houses, the house state of each sample house in the screened sample houses can be obtained from a background server of the house enterprise; wherein, the house status of each sample house is used for representing whether the sample house is sold currently, and in the case of sold, the house status of the sample house can be the sold status, otherwise, the house status of the sample house can be the on-sale status.
Next, it is possible to determine a sample house whose house state is a preset state among the sample houses screened according to the house state acquired from the background server, and acquire target information of at least one of the determined sample houses from the background server.
Specifically, in the case that the preset state is the sold state, house base information and achievement information of at least one of the determined sample houses may be acquired from the background server, and interpretation information including target information may be generated; the target information may include house base information including, but not limited to, a house area, a house type, a house floor, etc., and deal information including, but not limited to, a date of deal, a unit price of deal, a total price of deal, house image data at the time of deal, etc.
In the case that the preset state is the selling state, house base information of at least one sample house among the determined sample houses can be obtained from a background server, and interpretation information comprising target information is generated; the target information may include house base information including, but not limited to, house area, house type, house floor, etc.
Whether the preset state is a sold state or a selling state, after the interpretation information including the target information is generated, the interpretation information may be output by means of a screen display or the like.
Specifically, as shown in fig. 6, among the sample houses screened, three sample houses whose house status is a sold status may be used, the date of the transaction and the total price of the transaction for the first sample house are 2018, 12 months, 27 and 347 million, respectively, the date of the transaction and the total price of the transaction for the second sample house are 2018, 12 months, 20 and 280 ten thousand, respectively, and the date of the transaction and the total price of the transaction for the third sample house are 2018, 12 months, 10 and 300 ten thousand, respectively, and these date of the transaction and total price of the transaction may be located in the explanatory information and displayed through a screen.
In the implementation form, the interpretation information can assist the user to quickly know the related information of the sample house referenced when the house evaluation model evaluates the evaluation house, so as to assist the user to understand the origin of the evaluation result, thereby ensuring the convincing of the evaluation result.
Therefore, in the embodiment of the disclosure, the user can be effectively assisted in understanding the origin of the evaluation result by interpreting the output of the information, so as to ensure the convincing of the evaluation result.
It is to be noted that the manner of determining the sample house satisfying the preset condition among the sample houses screened is not limited thereto, and for example, a sample house whose preset attribute is matched with the evaluation house and whose house state is the preset state may be taken as the sample house satisfying the preset condition, or a sample house located in a neighboring cell of the cell to which the evaluation house belongs among the sample houses screened may be taken as the sample house satisfying the preset condition.
In an alternative example, according to the screened sample house, the interpretation information of the evaluation result of the house evaluation model on the evaluation house is output, including:
determining average price and total number of sample houses in the screened sample houses;
generating interpretation information of a house evaluation model on an evaluation result of evaluating the house; wherein, the interpretation information comprises the mapping relation of the obtained average price and the total quantity;
and outputting the interpretation information.
After screening out the sample houses referred to when the house evaluation model evaluates the evaluation houses, the total number of sample houses in the screened sample houses (hereinafter referred to as a second total number for convenience of distinction) may be calculated, and the house price of each sample house in the screened sample houses is obtained from the background server so as to calculate the average price of the sample houses in the screened sample houses (hereinafter referred to as a second average price for convenience of distinction). Next, interpretation information including a mapping relationship of the second average price and the second total number may be generated and output by means of voice playback, screen display, or the like.
Specifically, as shown in fig. 6, the interpretation information may include a mapping relationship of "total reference house source amount 284 sets" (which corresponds to the second total amount) and "1.62 tens of thousands/average" (which corresponds to the second average price), and the interpretation information may be displayed through a screen.
Therefore, in the embodiment of the disclosure, through the output of the interpretation information, the user can be assisted to quickly understand the relevant information of the sample house referenced when the house evaluation model evaluates the evaluation house, so as to assist the user to understand the origin of the evaluation result, thereby ensuring the convincing of the evaluation result.
Optionally, before the interpretation information is generated, the sample houses with preset attributes matched with the estimated houses may be further subdivided according to the cells to which they belong, so as shown in fig. 6, for each of the cell 1, the cell 2, and the cell 3, the number and average price of the sample houses matched with the house type attribute of the estimated houses and the house orientation attribute, and the number and average price of the sample houses matched with the house type attribute of the estimated houses, the house orientation attribute, and the house floor attribute may be respectively determined, and corresponding interpretation information may be generated according to the determination result.
In an alternative example, the implementation flow of the embodiment of the disclosure is mainly divided into four steps, which are respectively:
(1) Analyzing the house evaluation model to obtain an analysis result;
(2) Analyzing a training set, wherein the training set can comprise house basic information of a plurality of sample houses for training to obtain a house evaluation model, and paths of each sample data on each tree in the house evaluation model can be obtained through analyzing the training set and can be recorded; wherein any sample house can be represented in the form of a train sample (i);
(3) X is analyzed, X can be the basic information of the house of the evaluation house, the path of the evaluation house on each tree in the house evaluation model can be determined through X analysis, the paths can be recorded, and then sample houses on each tree which are consistent with the path of the evaluation house can be respectively determined; wherein the evaluation house is generally divided into different leaf nodes on each tree;
(4) And taking the determined sample house as a basis for valuation explanation, and outputting explanation information of the evaluation result according to the basis.
Therefore, the embodiment of the disclosure can obtain the whole prediction process of the estimated house in the house estimation model and the sample house sources referenced in the process, and can output the interpretation information which is convenient for the user to understand the estimation result by analyzing and sorting the sample house sources referenced in the process.
It should be noted that, in the prior art, when the house evaluation model is utilized to output the evaluation result, the evaluation result can only be strongly verified by average price and price trend of the cell where the house is located, for example, when a set of predicted unit price of 1.63 ten thousand per square meter is output, the average price of 1.53 ten thousand per square meter of the cell where the house is located is output, and the verification mode is less convincing. In comparison, the embodiment of the disclosure can reproduce the whole process of model valuation based on deep analysis of the model valuation result, so as to accurately analyze and explain the valuation result and output corresponding interpretation information, thereby effectively ensuring persuasion of the evaluation result.
Any of the house evaluation methods provided by the embodiments of the present disclosure may be performed by any suitable device having data processing capabilities, including, but not limited to: terminal equipment, servers, etc. Alternatively, any of the house evaluation methods provided by the embodiments of the present disclosure may be executed by a processor, such as the processor executing any of the house evaluation methods mentioned by the embodiments of the present disclosure by invoking corresponding instructions stored in a memory. And will not be described in detail below.
Exemplary apparatus
Fig. 7 is a schematic structural view of a house evaluation device provided in an exemplary embodiment of the present disclosure. The apparatus shown in fig. 7 includes a parsing module 701, a screening module 702, and an output module 703.
The analysis module 701 is configured to analyze the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses;
the screening module 702 is configured to screen, from a plurality of sample houses according to the analysis result, a sample house referred to when the house evaluation model evaluates the evaluation house;
and the output module 703 is used for outputting interpretation information of the evaluation result of the house evaluation model on the evaluation house according to the screened sample house.
In an alternative example, the house evaluation model comprises a plurality of trees, and the analysis result comprises structural information of each tree in the plurality of trees;
a screening module 702 comprising:
a first determining unit configured to determine a path of each of the plurality of sample houses on each tree according to the structure information in the analysis result, and evaluate the path of the house on each tree;
and the screening unit is used for screening the sample houses referenced by the house evaluation model when evaluating the evaluation houses from the plurality of sample houses according to the path of each sample house on each tree and the path of the evaluation house on each tree.
In an alternative example, the screening unit includes:
a first determining subunit configured to determine, from the path of each sample house on each tree and the path of the estimated house on each tree, a sample house, among the plurality of sample houses, that is consistent with the path of the estimated house on at least one tree;
and a second determination subunit for taking the determined sample house as a sample house referred to when evaluating the evaluation house by the house evaluation model.
In an alternative example, the output module 703 includes:
a second determining unit configured to determine sample houses satisfying a preset condition among the screened sample houses;
the first generation unit is used for generating interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the determined sample house;
and a first output unit for outputting the interpretation information.
In one example of an alternative implementation of the method,
the second determining unit is specifically configured to:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
a first generation unit including:
a first acquisition subunit for acquiring the determined average price and total number of sample houses in the sample houses;
A first generation subunit for generating interpretation information of the evaluation result of the evaluation house by the house evaluation model; wherein, the interpretation information comprises the mapping relation of the obtained average price and the total number.
In one example of an alternative implementation of the method,
the second determining unit is specifically configured to:
determining a sample house with a house state being a preset state in the screened sample houses;
a first generation unit including:
a second acquisition subunit configured to acquire target information of at least one of the determined sample houses;
the second generation subunit is used for generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; the interpretation information comprises target information, wherein the target information comprises house basic information and achievement information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
In an alternative example, the output module 703 includes:
an acquisition unit for acquiring average prices and total numbers of sample houses among the screened sample houses;
a second generation unit configured to generate interpretation information of an evaluation result of the evaluation house by the house evaluation model; wherein, the interpretation information comprises the mapping relation of the obtained average price and the total quantity;
And a second output unit for outputting the interpretation information.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present disclosure is described with reference to fig. 8. The electronic device may be either or both of the first device and the second device, or a stand-alone device independent thereof, which may communicate with the first device and the second device to receive the acquired input signals therefrom.
Fig. 8 illustrates a block diagram of an electronic device 80 according to an embodiment of the present disclosure.
As shown in fig. 8, the electronic device 80 includes one or more processors 81 and memory 82.
In one example, the electronic device 80 may further include: an input device 83 and an output device 84, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
For example, where the electronic device 80 is a first device or a second device, the input means 83 may be a microphone or an array of microphones. When the electronic device 80 is a stand-alone device, the input means 83 may be a communication network connector for receiving the acquired input signals from the first device 1 and the second device.
In addition, the input device 83 may also include, for example, a keyboard, a mouse, and the like.
The output device 84 may output various information to the outside, and the output device 84 including the determined distance information, direction information, etc. may include, for example, a display, a speaker, a printer, and a communication network and a remote output device connected thereto, etc.
Of course, only some of the components of the electronic device 80 relevant to the present disclosure are shown in fig. 8, with components such as buses, input/output interfaces, etc. omitted for simplicity. In addition, the electronic device 80 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in a house assessment method according to various embodiments of the present disclosure described in the "exemplary methods" section of the present description.
The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform the steps in a house evaluation method according to various embodiments of the present disclosure described in the above "exemplary method" section of the present description.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, so that the same or similar parts between the embodiments are mutually referred to. For system embodiments, the description is relatively simple as it essentially corresponds to method embodiments, and reference should be made to the description of method embodiments for relevant points.
The block diagrams of the devices, apparatuses, devices, systems referred to in this disclosure are merely illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the apparatus, devices and methods of the present disclosure, components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered equivalent to the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the disclosure to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (14)
1. A house evaluation method, comprising:
analyzing the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses;
screening sample houses referenced when the house evaluation model evaluates the evaluation house from the plurality of sample houses according to the analysis result;
according to the screened sample houses, outputting interpretation information of the house evaluation model on the evaluation results of the evaluation houses;
the house evaluation model comprises a plurality of trees, and the analysis result comprises structural information of each tree in the plurality of trees;
and screening sample houses referenced by the house evaluation model when evaluating the evaluation house from the plurality of sample houses according to the analysis result, wherein the sample houses comprise:
Determining a path of each sample house in the plurality of sample houses on each tree according to the structure information in the analysis result, and evaluating the path of the house on each tree;
and screening sample houses referenced by the house evaluation model when evaluating the evaluation houses from the plurality of sample houses according to the path of each sample house on each tree and the path of the evaluation house on each tree.
2. The method of claim 1, wherein the screening the sample houses from the plurality of sample houses for reference in evaluating the evaluation house by the house evaluation model based on the path of each sample house on each tree and the path of the evaluation house on each tree comprises:
determining a sample house consistent with the path of the evaluation house on at least one tree in the plurality of sample houses according to the path of each sample house on each tree and the path of the evaluation house on each tree;
and taking the determined sample house as a sample house which is referred when the house evaluation model evaluates the evaluation house.
3. The method according to any one of claims 1 to 2, wherein the outputting of interpretation information of the evaluation result of the evaluation house by the house evaluation model according to the screened sample house includes:
determining sample houses meeting preset conditions in the screened sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the determined sample house;
and outputting the interpretation information.
4. The method of claim 3, wherein the step of,
the determining the sample house meeting the preset condition in the screened sample houses comprises the following steps:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
the generating, according to the determined sample house, interpretation information of the house evaluation model on the evaluation result of the evaluation house includes:
obtaining average price and total number of the sample houses in the determined sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; wherein the interpretation information comprises the obtained mapping relation of average price and total quantity.
5. The method of claim 3, wherein the step of,
the determining the sample house meeting the preset condition in the screened sample houses comprises the following steps:
determining a sample house with a house state being a preset state in the screened sample houses;
the generating, according to the determined sample house, interpretation information of the house evaluation model on the evaluation result of the evaluation house includes:
acquiring target information of at least one sample house in the determined sample houses;
generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; the interpretation information comprises the target information, wherein the target information comprises house basic information and deal information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
6. The method according to any one of claims 1 to 2, wherein the outputting of interpretation information of the evaluation result of the evaluation house by the house evaluation model according to the screened sample house includes:
obtaining average price and total number of sample houses in the screened sample houses;
Generating interpretation information of the house evaluation model on the evaluation result of the evaluation house; wherein the interpretation information comprises the obtained mapping relation between average price and total quantity;
and outputting the interpretation information.
7. A house evaluating device, characterized by comprising:
the analysis module is used for analyzing the house evaluation model to obtain an analysis result; the house evaluation model is obtained through training according to house data of a plurality of sample houses;
the screening module is used for screening sample houses referenced when the house evaluation model evaluates the evaluation houses from the plurality of sample houses according to the analysis result;
the output module is used for outputting interpretation information of the house evaluation model on the evaluation result of the evaluation house according to the screened sample house;
the house evaluation model comprises a plurality of trees, and the analysis result comprises structural information of each tree in the plurality of trees;
the screening module comprises:
a first determining unit configured to determine a path of each of the plurality of sample houses on each tree, and a path of the evaluation house on each tree, based on the structure information in the analysis result;
A screening unit for screening, from the plurality of sample houses, a sample house to which the house evaluation model refers when evaluating the evaluation house, based on a path of each sample house on each tree and a path of the evaluation house on each tree.
8. The apparatus of claim 7, wherein the screening unit comprises:
a first determining subunit configured to determine, from the path of each sample house on each tree and the path of the evaluation house on each tree, a sample house, among the plurality of sample houses, that is consistent with the path of the evaluation house on at least one tree;
and a second determination subunit configured to use the determined sample house as a sample house referred to when the house evaluation model evaluates the evaluation house.
9. The apparatus according to any one of claims 7 to 8, wherein the output module comprises:
a second determining unit configured to determine sample houses satisfying a preset condition among the screened sample houses;
a first generation unit configured to generate interpretation information of an evaluation result of the evaluation house by the house evaluation model, based on the determined sample house;
And a first output unit for outputting the interpretation information.
10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
the second determining unit is specifically configured to:
determining sample houses with preset attributes matched with the evaluation houses in the screened sample houses;
the first generation unit includes:
a first acquisition subunit for acquiring the determined average price and total number of sample houses in the sample houses;
a first generation subunit for generating interpretation information of the evaluation result of the house evaluation by the house evaluation model; wherein the interpretation information comprises the obtained mapping relation of average price and total quantity.
11. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
the second determining unit is specifically configured to:
determining a sample house with a house state being a preset state in the screened sample houses;
the first generation unit includes:
a second acquisition subunit configured to acquire target information of at least one of the determined sample houses;
a second generation subunit, configured to generate interpretation information of the evaluation result of the evaluation house by the house evaluation model; the interpretation information comprises the target information, wherein the target information comprises house basic information and deal information under the condition that the preset state is a sold state, and the target information comprises the house basic information under the condition that the preset state is a sold state.
12. The apparatus according to any one of claims 7 to 8, wherein the output module comprises:
an acquisition unit for acquiring average prices and total numbers of sample houses among the screened sample houses;
a second generation unit configured to generate interpretation information of an evaluation result of the evaluation house by the house evaluation model; wherein the interpretation information comprises the obtained mapping relation between average price and total quantity;
and a second output unit for outputting the interpretation information.
13. A computer-readable storage medium storing a computer program for executing the house assessment method according to any one of the preceding claims 1-6.
14. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor being configured to read the executable instructions from the memory and execute the instructions to implement the house assessment method of any of the preceding claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089786.4A CN111340527B (en) | 2020-02-13 | 2020-02-13 | House assessment method, house assessment device, computer readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089786.4A CN111340527B (en) | 2020-02-13 | 2020-02-13 | House assessment method, house assessment device, computer readable storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111340527A CN111340527A (en) | 2020-06-26 |
| CN111340527B true CN111340527B (en) | 2023-06-20 |
Family
ID=71183437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010089786.4A Active CN111340527B (en) | 2020-02-13 | 2020-02-13 | House assessment method, house assessment device, computer readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111340527B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233103B (en) * | 2020-10-26 | 2021-09-21 | 贝壳找房(北京)科技有限公司 | Three-dimensional house model quality evaluation method and device and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274105A (en) * | 2017-06-28 | 2017-10-20 | 山东大学 | Multiple attribute decision making (MADM) tree stabilization of power grids nargin appraisal procedure based on linear discriminant analysis |
| CN107808004A (en) * | 2017-11-15 | 2018-03-16 | 北京百度网讯科技有限公司 | Model training method and system, server, storage medium |
| CN108416707A (en) * | 2018-02-07 | 2018-08-17 | 链家网（北京）科技有限公司 | House house type appraisal procedure and device |
| CN109886775A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | House advantage and disadvantage appraisal procedure, device, equipment and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121750B (en) * | 2016-11-30 | 2022-07-08 | 西门子公司 | Model processing method and device and machine readable medium |
-
2020
- 2020-02-13 CN CN202010089786.4A patent/CN111340527B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274105A (en) * | 2017-06-28 | 2017-10-20 | 山东大学 | Multiple attribute decision making (MADM) tree stabilization of power grids nargin appraisal procedure based on linear discriminant analysis |
| CN107808004A (en) * | 2017-11-15 | 2018-03-16 | 北京百度网讯科技有限公司 | Model training method and system, server, storage medium |
| CN108416707A (en) * | 2018-02-07 | 2018-08-17 | 链家网（北京）科技有限公司 | House house type appraisal procedure and device |
| CN109886775A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | House advantage and disadvantage appraisal procedure, device, equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 马艺文 ; 孟成 ; 潘琛玲 ; .基于C5.0决策树的征收房屋价值评估模型研究.地理空间信息.2018,(10),第32-34、37. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111340527A (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Augenstein et al. | Generative models for effective ML on private, decentralized datasets | |
| Moundigbaye et al. | Which panel data estimator should I use?: A corrigendum and extension | |
| CN108197652B (en) | Method and apparatus for generating information | |
| CN109783704B (en) | Man-machine hybrid response method, system and device | |
| EP3432228A1 (en) | Expandability retention device | |
| CN113326900A (en) | Data processing method and device of federal learning model and storage medium | |
| CN114004352B (en) | Simulation implementation method, neural network compiler and computer readable storage medium | |
| CN111583017A (en) | Risk strategy generation method and device based on guest group positioning and electronic equipment | |
| CN111340527B (en) | House assessment method, house assessment device, computer readable storage medium and electronic equipment | |
| CN111949785A (en) | Query statement management method and device, readable storage medium and electronic device | |
| Velmurugan et al. | Developing a fidelity evaluation approach for interpretable machine learning | |
| CN111062490A (en) | Method and device for processing network data containing private data | |
| CN109711849B (en) | Ether house address portrait generation method and device, electronic equipment and storage medium | |
| Regular et al. | SimSurvey: an R package for comparing the design and analysis of surveys by simulating spatially-correlated populations | |
| CN113010791B (en) | Search result display processing method and device and computer readable storage medium | |
| CN116932735A (en) | Text comparison method, device, medium and equipment | |
| CN116738293A (en) | Service evaluation processing method and device and electronic equipment | |
| CN111582647A (en) | User data processing method and device and electronic equipment | |
| CN115033785A (en) | Post recommendation method and device, readable storage medium and electronic equipment | |
| US20220366264A1 (en) | Procedurally generating realistic interfaces using machine learning techniques | |
| CN112766320A (en) | Classification model training method and computer equipment | |
| CN112328871A (en) | Reply generation method, device, equipment and storage medium based on RPA module | |
| CN112102062A (en) | Risk assessment method and device based on weak supervised learning and electronic equipment | |
| Garner | Clojure for data science | |
| US11669681B2 (en) | Automated calculation predictions with explanations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |