House resource information display method, electronic equipment and computer program product

Abstract

The invention provides a housing resource information display method, electronic equipment and a computer program product. The housing resource information display method comprises the steps of obtaining a first score of a target housing resource, and obtaining user interaction information of the target housing resource and / or a feature vector of the target housing resource; on the basis of feature vector information and / or user interaction information of the first house resource, a first score of the first house resource is adjusted, the adjusted first score of the first house resource is obtained, and the feature vector information comprises a feature vector of the first house resource and feature vectors of m second house resources; the first housing resources are target housing resources which are not determined to be ranked in the housing resource information display sequence, the second housing resources are target housing resources which are determined to be ranked in the housing resource information display sequence, and m is a positive integer; based on the adjusted first score, determining the ranking of the first housing resource in the housing resource information display sequence; and displaying the housing resource information of the plurality of target housing resources based on the housing resource information display sequence.

Description

Technical Field

[0001] The present disclosure relates to the technical field of computers and the like, and particularly to a method for displaying housing source information, an electronic device, and a computer program product. Background Art

[0002] In the real estate field, there are a large number of housing sources, and it is crucial to display these numerous housing sources reasonably.

[0003] In the related art, the housing source information of housing sources under different services is displayed in fixed different areas. Only the housing source information of multiple housing sources under one service is displayed in one area, and the housing source information of the multiple housing sources displayed in the same area is sorted based on the click-through rate of the housing sources. Such a display method is unreasonable and is not conducive to the full display of the housing source information of a large number of housing sources. Summary of the Invention

[0004] The present disclosure provides a method for displaying housing source information, an electronic device, a readable storage medium, and a computer program product.

[0005] According to one aspect of the present disclosure, there is provided a method for displaying housing source information, including: Obtaining a first score of a target housing source, and obtaining user interaction information of the target housing source and / or a feature vector of the target housing source; Adjusting the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain an adjusted first score of the first housing source, where the feature vector information includes the feature vector of the first housing source and the feature vectors of m second housing sources, the first housing source is a target housing source for which the ranking in the housing source information display order has not been determined, the second housing source is a target housing source for which the ranking in the housing source information display order has been determined, and m is a positive integer; Determining the ranking of the first housing source in the housing source information display order based on the adjusted first score; and Displaying the housing source information of multiple target housing sources based on the housing source information display order.

[0006] According to the housing source information display method of at least one embodiment of the present disclosure, adjusting the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain an adjusted first score of the first housing source includes: Determining a first coefficient according to the user interaction information of the first housing source; and Adjusting the first score of the first housing source based on the first coefficient to obtain an adjusted first score of the first housing source.

[0007] The method for displaying housing source information according to at least one embodiment of the present disclosure determines a first coefficient based on the user interaction information of the first housing source, including: Based on the mapping relationship between keywords in the user interaction information and preset values, determine the preset value corresponding to the user interaction information of the first housing source; and Based on the preset value corresponding to the user interaction information of the first housing source, adjust the preset coefficient to obtain the first coefficient.

[0008] The method for displaying housing source information according to at least one embodiment of the present disclosure adjusts the first score of the first housing source based on the first coefficient to obtain the adjusted first score of the first housing source, including: Multiply the first score of the first housing source by the first coefficient to obtain the adjusted first score of the first housing source.

[0009] The method for displaying housing source information according to at least one embodiment of the present disclosure adjusts the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain the adjusted first score of the first housing source, including: Calculate the similarity between the feature vectors of each second housing source among the m second housing sources and the feature vector of the first housing source; Calculate the mean value of the m similarities; and Based on the mean value, adjust the first score of the first housing source to obtain the adjusted first score of the first housing source.

[0010] The method for displaying housing source information according to at least one embodiment of the present disclosure adjusts the first score of the first housing source based on the mean value to obtain the adjusted first score of the first housing source, including: Perform weighted summation on the first score of the first housing source and the mean value to obtain the adjusted first score of the first housing source.

[0011] The method for displaying housing source information according to at least one embodiment of the present disclosure adjusts the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain the adjusted first score of the first housing source, including: Determine a first coefficient according to the user interaction information of the first housing source; Calculate the similarity between the feature vectors of each second housing source among the m second housing sources and the feature vector of the first housing source; Calculate the mean value of the m similarities; and Multiply the weighted sum of the first score of the first housing source and the mean value by the first coefficient to obtain the adjusted first score of the first housing source.

[0012] The method for displaying housing source information according to at least one embodiment of the present disclosure, before adjusting the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source, further includes: Determine a target ranking in the housing source information display order; In the process of determining the target housing source located at the target ranking, determine whether the n second housing sources meet the target business rules, where n is a positive integer; Adjusting the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source includes: In the case that the n second housing sources do not meet the target business rules, for each first housing source among the multiple first housing sources, adjust the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain the adjusted first score of the first housing source; Determining the ranking of the first housing source in the housing source information display order based on the adjusted first score includes: Based on the adjusted first score, determine a first housing source located at the target ranking from the multiple first housing sources.

[0013] The method for displaying housing source information according to at least one embodiment of the present disclosure, after determining whether the n second housing sources meet the target business rules, further includes: In the case that the n second housing sources meet the target business rules, based on the first score of the first housing source, determine a first housing source located at the target ranking from the multiple first housing sources.

[0014] The method for displaying housing source information according to at least one embodiment of the present disclosure further includes: In the case that there is no second housing source, based on the first score of the target housing source, determine the ranking of a preset number of target housing sources in the housing source information display order.

[0015] The method for displaying housing source information according to at least one embodiment of the present disclosure, before obtaining the first score of the target housing source, further includes: In response to the user-triggered display of housing source information, obtain the user portrait and the second score of each housing source among the multiple housing sources; For each housing source among the multiple housing sources, adjust the second score of the housing source based on the user portrait to obtain the adjusted second score of the housing source; and Based on the adjusted second score of the housing source, determine the target housing source from the multiple housing sources.

[0016] According to another aspect of the present disclosure, there is provided an electronic device, including: a memory that stores execution instructions; and a processor that executes the execution instructions stored in the memory, such that the processor executes the housing source information display method according to any one of the embodiments of the present disclosure.

[0017] According to still another aspect of the present disclosure, there is provided a readable storage medium in which execution instructions are stored, and when the execution instructions are executed by a processor, they are used to implement the housing source information display method according to any one of the embodiments of the present disclosure.

[0018] According to yet another aspect of the present disclosure, there is provided a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the housing source information display method according to any one of the embodiments of the present disclosure. Description of the Drawings

[0019] The drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, are used to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are included in this specification and form a part of this specification.

[0020] Figure 1 It is a flowchart of a housing source information display method according to an embodiment of the present disclosure.

[0021] Figure 2 It is a schematic diagram of the process of adjusting the first score according to an embodiment of the present disclosure.

[0022] Figure 3 It is a schematic diagram of the process of adjusting the first score according to another embodiment of the present disclosure.

[0023] Figure 4 It is a schematic diagram of the process of adjusting the first score according to yet another embodiment of the present disclosure.

[0024] Figure 5 It is a schematic diagram of the process of adjusting the first score according to still another embodiment of the present disclosure.

[0025] Figure 6 It is a schematic diagram of the process of determining a target housing source according to an embodiment of the present disclosure.

[0026] Figure 7 It is a flowchart of a housing source information display method according to another embodiment of the present disclosure.

[0027] Figure 8 It is a schematic block diagram of the structure of a housing source information display device according to an embodiment of the present disclosure.

[0028] Figure 9It is a schematic block diagram of the structure of an electronic device according to an embodiment of the present disclosure. Specific Embodiments

[0029] The present disclosure will be further described in detail below in conjunction with the accompanying drawings and examples. It can be understood that the specific examples described herein are only for explaining the relevant content and do not limit the present disclosure. Additionally, it should be noted that for ease of description, only the parts related to the present disclosure are shown in the drawings.

[0030] It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The technical solutions of the present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0031] In the related art, the housing source information of housing sources under different services is displayed in fixed different areas. Only the housing source information of multiple housing sources under one service is displayed in one area, and the housing source information of the multiple housing sources displayed in the same area is sorted based on the click-through rate of the housing sources. This will result in the housing sources with high click-through rates in each area always being preferentially displayed, and the housing sources with low click-through rates always being difficult to be displayed because they are ranked behind. Since the housing sources preferentially displayed have a greater probability of being clicked by users, and the housing sources displayed behind have a smaller probability of being clicked by users, and the number of clicks is usually proportional to the click-through rate, therefore, as the number of displays increases, the click-through rate of the housing sources preferentially displayed will gradually increase, while the click-through rate of the housing sources displayed behind is difficult to improve, thereby causing a relatively large Matthew effect, resulting in the housing source information of some housing sources not being displayed and some housing sources being vacant for a long time. At the same time, over time, it will lead to the formation of an information cocoon for finding housing on the user side, causing users not to see more housing sources that may conclude transactions.

[0032] Therefore, the present disclosure proposes a method for displaying housing source information.

[0033] The housing source information display method of the present disclosure can be used for an electronic device to reasonably determine the housing source information display order based on the user interaction information of the housing source and / or the feature vector of the housing source, and display the housing source information based on the housing source information display order. In the present disclosure, the electronic device includes but is not limited to a server, a mobile phone, a tablet computer, a laptop computer, a personal computer, a wearable device, an ATM, etc.

[0034] For ease of description and to make the technical solutions of the specific embodiments of the present disclosure easier to understand, before describing the housing source information display method implemented in the present disclosure, the technical terms involved in the specific embodiments of the present disclosure are explained as follows: A housing source refers to a house available for sale, rent, or display.

[0035] Housing source information refers to the basic information of a housing source, such as its location, area, house type, price, image, etc.

[0036] Click-through rate refers to the ratio of the number of times a certain object on the display page is clicked to the number of times it is displayed.

[0037] Business opportunity volume refers to the number of times a housing listing is triggered for a specific operation (such as contacting a broker).

[0038] Figure 1 The overall flowchart of the housing listing information display method M100 according to an embodiment of the present disclosure is shown. As Figure 1 shown, the method includes steps S110 to S140. Among them, the method can be executed by an electronic device such as a server, a mobile phone, a computer, etc.

[0039] Specifically, Figure 1 the shown method includes: S110. Obtain the first score of the target housing listing, and obtain the user interaction information of the target housing listing and / or the feature vector of the target housing listing; Exemplarily, the first score can be the click-through rate, or the business opportunity volume, or other numerical values related to the display order of the housing listing information of the target housing listing. The first score of each target housing listing can be calculated or predicted periodically and automatically. For example, when the first score is the click-through rate, user characteristics, target housing listing characteristics, and context characteristics can be input into a trained click-through rate (CTR) prediction model, and the CTR prediction model can be used to predict the click-through rate of each target housing listing, so as to obtain the click-through rate of each target housing listing. User characteristics include but are not limited to user age, user gender, housing listings clicked by the user, housing listings traded by the user, etc., target housing listing characteristics include but are not limited to target housing listing id, number of times the target housing listing is clicked, number of times the housing listing information of the target housing listing is displayed, etc., and context characteristics include but are not limited to user login device, time, etc. The CTR prediction model can be any one of logistic regression (LR), factorization machines (FM), deep neural networks (DNN), and Transformer-based models.

[0040] The user interaction information of the target housing listing includes but is not limited to the number of clicks, business opportunities (such as contacting a broker), appointment viewing times, and offline viewing times triggered by the user for the target housing listing within a specific period. The user interaction information is closely related to the target housing listing. Therefore, obtaining the user interaction information of the target housing listing is beneficial to providing data support for housing listing information display and making the housing listing information display method more reasonable.

[0041] The feature vector of the target housing unit can be obtained through a trained feature extraction model. The feature extraction model includes but is not limited to the PinSAGE graph model and the deep learning model. In one example, a PinSAGE graph model is constructed based on the housing units clicked by each user among multiple users, the click order between different housing units, and the stay duration on each housing unit, and the constructed PinSAGE graph model is trained to obtain a trained PinSAGE graph model, and then the feature vector of the target housing unit can be obtained from the trained PinSAGE graph model. In this way, the feature vector of the target housing unit can represent information in multiple dimensions of the target housing unit, which is beneficial to providing data support for housing unit information display and making the housing unit information display method more reasonable.

[0042] S120. Adjust the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit to obtain the adjusted first score of the first housing unit, where the feature vector information includes the feature vector of the first housing unit and the feature vectors of m second housing units, the first housing unit is a target housing unit whose ranking in the housing unit information display order has not been determined, the second housing units are target housing units whose rankings in the housing unit information display order have been determined, and m is a positive integer; The value of m can be set according to actual needs. The feature vectors of the m second housing units are the feature vectors of each of the m second housing units. The m second housing units can be the m newly determined second housing units, or any m second housing units among the multiple already determined second housing units, or all the already determined second housing units, which is not limited here.

[0043] Exemplarily, the first score of the first housing unit can be adjusted based on the user interaction information of the first housing unit to obtain the adjusted first score of the first housing unit; or the first score of the first housing unit can be adjusted based on the feature vector information to obtain the adjusted first score of the first housing unit; or the first score of the first housing unit can be adjusted based on the user interaction information and the feature vector information of the first housing unit to obtain the adjusted first score of the first housing unit, which is not limited here.

[0044] It should be noted that the obtained adjusted first score will not replace or overwrite the first score. That is to say, in this disclosure, after obtaining the adjusted first score, if the first score is mentioned again for adjustment, it is the first score that is adjusted, rather than the adjusted first score. If the first score of a target housing unit is adjusted to obtain an adjusted first score, and then the first score of the target housing unit is adjusted again to obtain another adjusted first score, the latest obtained adjusted first score shall prevail.

[0045] S130. Determine the ranking of the first housing unit in the display order of housing unit information based on the adjusted first score; Since the adjusted first score is obtained by considering the feature vector information and / or the user interaction information of the first housing unit on the basis of the first score, the adjusted first score is more reasonable. Consequently, the ranking of the first housing unit determined based on the adjusted first score in the display order of housing unit information is more reasonable.

[0046] Exemplarily, after determining the adjusted first scores of all the first housing units, the ranking of all the first housing units in the display order of housing unit information can be directly determined based on the magnitude order of the adjusted first scores; alternatively, based on the magnitude order of the adjusted first scores, only the ranking of a part of the first housing units in the display order of housing unit information can be determined, and the ranking of the remaining part of the first housing units in the display order of housing unit information can be determined based on a preset algorithm.

[0047] S140. Display the housing unit information of multiple target housing units based on the display order of housing unit information.

[0048] In the housing unit information display method according to the embodiments of the present disclosure, based on the user interaction information and / or the feature vector information of the target housing units (i.e., the first housing units) whose rankings in the display order of housing unit information have not been determined (i.e., the feature vectors of the target housing units whose rankings in the display order of housing unit information have not been determined and the feature vectors of m target housing units whose rankings in the display order of housing unit information have been determined), the first score of the target housing units whose rankings in the display order of housing unit information have not been determined is adjusted to obtain the adjusted first score of the target housing units whose rankings in the display order of housing unit information have not been determined. Then, based on the adjusted first score, the ranking of the first housing units in the display order of housing unit information is determined, thereby facilitating the reasonable display of the housing unit information of multiple target housing units based on the display order of housing unit information. Since the adjusted first score is obtained by considering the feature vector information and / or the user interaction information of the first housing unit on the basis of the first score, the adjusted first score is more reasonable than the first score. Consequently, the ranking of the first housing units determined based on the adjusted first score in the display order of housing unit information is more reasonable, which is conducive to the full display of the housing unit information of different target housing units. At the same time, since the target housing units under different services can be displayed based on the same display order of housing unit information, that is, the housing units under different services are not displayed by region, the housing units under different services have the opportunity to be displayed simultaneously, which further facilitates the full display of the housing unit information of different target housing units.

[0049] Regarding step S120, as a possible implementation manner, it may include steps S1211 and S1212 as Figure 2 shown.

[0050] S1211. Determine a first coefficient according to the user interaction information of the first housing source.

[0051] The user interaction information may be text and cannot directly act on the first score in numerical form. Therefore, the user interaction information of the first housing source is converted into a numerical first coefficient, which is convenient for acting on the first score.

[0052] As a possible implementation manner, step S1211 may include: determining a preset value corresponding to the user interaction information of the first housing source based on the mapping relationship between keywords in the user interaction information and preset values; and adjusting a preset coefficient based on the preset value corresponding to the user interaction information of the first housing source to obtain a first coefficient. In this way, through the mapping relationship between keywords in the user interaction information and preset values, the user interaction information is accurately converted into a numerical preset value, and then the preset coefficient is adjusted by the preset value to obtain an accurate first coefficient. The whole process is more scientific and accurate, and the mapping relationship and preset coefficient can be dynamically adjusted according to requirements, with stronger flexibility.

[0053] Exemplarily, the preset values corresponding to different keywords in the user interaction information are different. If the user interaction information includes multiple keywords, the preset coefficient is adjusted based on the largest preset value corresponding to the multiple keywords. For example, the preset value corresponding to two clicks in the user interaction information is 1, the preset value corresponding to triggering one business opportunity is 2, the preset value corresponding to triggering two business opportunities is 3, the preset value corresponding to triggering a viewing appointment is 4, and the preset value corresponding to triggering an in-person viewing is 5. In this way, the deeper the user's interaction degree with the target housing source, the greater the degree of adjustment of the target housing source, which is conducive to the full display of the housing source information of different target housing sources. If the keyword in the mapping relationship does not exist in the user interaction information, the preset value can take a default value, such as 0.

[0054] The first coefficient α can be calculated by the following formula: α = (1 - τ) n, where n is the maximum preset value corresponding to the keyword in the user interaction information, and τ is a preset coefficient. In this way, the larger the preset value and the preset coefficient, the smaller the first coefficient, achieving personalized weight reduction. τ can be set according to actual needs, for example, set to a fixed value of 0.1. τ can also be dynamically adjusted according to the number of keywords included in the user interaction information. The more keywords, the larger τ; the fewer keywords, the smaller τ. Specifically, the preset coefficient corresponding to the number of keywords can be accurately determined based on the mapping relationship between the number of keywords and the preset coefficient. For example, if the number of keywords is 1, that is, the user interaction information includes one of two clicks, triggering one business opportunity, triggering two business opportunities, triggering a reservation for a property viewing, triggering an in-person property viewing, then τ is 0.1; if the number of keywords is 4, that is, the user interaction information includes four of two clicks, triggering one business opportunity, triggering two business opportunities, triggering a reservation for a property viewing, triggering an in-person property viewing, then τ is 0.4. In this way, the deeper the user's interaction with the target property, the greater the degree of adjustment of the target property, which is conducive to the full display of the property information of different target properties.

[0055] As another possible implementation, step S1211 may include: directly determining the first coefficient corresponding to the user interaction information of the first property information based on the mapping relationship between the keyword and the first coefficient in the user interaction information. In this way, it is beneficial to more quickly and accurately determine the first coefficient.

[0056] S1212. Adjust the first score of the first property based on the first coefficient to obtain the adjusted first score of the first property.

[0057] As a possible implementation, the first coefficient is greater than 0 and less than or equal to 1. Correspondingly, step S1212 may include: multiplying the first score of the first property by the first coefficient to obtain the adjusted first score of the first property. In this way, the smaller the first coefficient, the smaller the adjusted first score, and the adjusted first score can be less than the first score. Therefore, when sorting based on the adjusted first score, it is beneficial to reduce the ranking of properties that have interacted with the user or interacted more in the display order of property information, making it more likely for other properties that have not interacted with the user or interacted less to be preferentially displayed. Moreover, the adjustment of the first score is achieved through a simple multiplication operation, with high calculation efficiency and easy implementation. At the same time, the first coefficient directly acts on the first score, which can intuitively reflect the impact of user interaction information on sorting.

[0058] As another possible implementation, the first coefficient is a positive number. Correspondingly, step S1212 may include: obtaining the adjusted first score of the first housing source by subtracting the first coefficient from the first score of the first housing source. In this way, the larger the first coefficient, the smaller the adjusted first score, and the adjusted first score may be less than the first score. Therefore, when sorting based on the adjusted first score, it is beneficial to reduce the ranking of the first housing source in the display order of housing source information, so that other housing sources that have not interacted with the user or have interacted less with the user have a greater possibility of being preferentially displayed.

[0059] For the housing source information display method in the above implementation, the first coefficient is determined according to the user interaction information of the first housing source, and based on the first coefficient, the first score of the first housing source is adjusted to obtain the adjusted first score of the first housing source. Thus, by introducing the first coefficient, the specific influence mode of the user interaction information on the adjustment of the first score of the first housing source is clarified, the adjustment process is simplified, and the introduction of the first coefficient makes the adjustment process more transparent, facilitating subsequent analysis and optimization.

[0060] Regarding step S120, as another possible implementation, it may include steps S1221 to S1223 as Figure 3 shown.

[0061] S1221. Calculate the similarity between the feature vectors of each second housing source among the m second housing sources and the feature vector of the first housing source.

[0062] The value of m can be set according to actual needs. The larger m is, the more similarities between the first housing source and more second housing sources will be considered in the adjustment process of the first score of the first housing source. In one example, m can take any value among 3, 4, 5, 6, 7, 8, 9, and 10. In one example, the housing sources corresponding to each ranking in the housing source information display order are determined in sequence. Furthermore, in the form of a sliding window, when the ranking of a housing source to be determined enters the sliding window, the feature vectors of the housing sources corresponding to the rankings of the other housing sources that have already been determined in the sliding window can be used for similarity calculation. For example, if the length of the sliding window is 4, when determining the housing source corresponding to the 4th ranking in the sliding window, the rankings of the first 3 housing sources in the sliding window have been determined, and then the similarities between the feature vectors of these 3 housing sources and the feature vector of the first housing source can be calculated.

[0063] It should be noted that the specific numerical values mentioned in this disclosure are only for detailed illustration of the implementation of this disclosure as examples, and should not be construed as a limitation of this disclosure. In other examples or implementations or embodiments, other numerical values can be selected according to this disclosure, and no specific limitation is made here.

[0064] Exemplarily, the similarity may be one of cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient. Preferably, calculate the cosine similarity between the feature vectors of each of the m second housing units and the feature vector of the first housing unit.

[0065] By calculating the similarity, the similarity degree between the first housing unit and the second housing units can be better determined, thereby providing support for adjusting the first score of the first housing unit. For example, if it is desired that the first housing units to be sorted next are as dissimilar to the second housing units as possible, the first scores of the first housing units similar to the second housing units can be minimized and / or the first scores of the first housing units dissimilar to the second housing units can be maximized; if it is desired that the first housing units to be sorted next are as similar to the second housing units as possible, the first scores of the first housing units similar to the second housing units can be maximized and / or the first scores of the first housing units dissimilar to the second housing units can be minimized.

[0066] S1222. Calculate the mean of the m similarities.

[0067] Exemplarily, the mean of the m similarities corresponding to a first housing unit d can be calculated by the following formula: , where is the i-th second housing unit among the m second housing units, is the similarity between a first housing unit d and the i-th second housing unit .

[0068] Exemplarily, the mean similarity of each first housing unit with the m second housing units needs to be calculated.

[0069] S1223. Based on the mean, adjust the first score of the first housing unit to obtain the adjusted first score of the first housing unit.

[0070] Exemplarily, step S1223 may be: perform weighted summation on the first score of the first housing unit and the mean to obtain the adjusted first score of the first housing unit. In this way, by combining the similarity mean and the first score through weighted summation, while retaining part of the original score information (i.e., the first score), the influence of similarity can be fully considered. And different weights can be assigned to the mean and the first score according to actual needs, enhancing the flexibility and adaptability of the method.

[0071] In one example, the adjusted first score score is calculated by the following formula: score = (1 - β) × ctr(d) - β × s(d), where ctr(d) is the first score of a first housing unit d, s(d) is the mean of m similarities corresponding to a first housing unit d, and 1 - β and -β are weights respectively. The weight multiplied by s(d) is negative, which is beneficial for the first housing units with greater similarity to m second housing units to have smaller adjusted first scores, while the first housing units with smaller similarity to m second housing units to have larger adjusted first scores, so as to facilitate the preferential screening of the first housing units with greater differences from m second housing units and improve diversity. β can be a parameter between 0 and 1, used to control the balance between the first score and the mean similarity. When β is close to 1, the algorithm pays more attention to the mean similarity (i.e., diversity); when β is close to 0, the algorithm pays more attention to the first score (such as the conversion rate). Therefore, by adjusting β, the adjustment of the first score can be made more controllable. The value of β can be preset by relevant personnel, or automatically adjusted by the electronic device based on the feedback data of the user on the displayed housing unit information (such as review text and / or score). For example, if it is detected that the feedback data indicates that the user is not satisfied with the sorting effect, then β is decreased or increased according to the preset gradient value.

[0072] For the housing unit information display method of the above embodiment, calculate the similarity between the feature vectors of each second housing unit in m second housing units and the feature vector of the first housing unit, calculate the mean of m similarities, and based on the mean, adjust the first score of the first housing unit to obtain the adjusted first score of the first housing unit. Thus, the adjusted first score of the first housing unit is obtained by considering the feature vectors of m second housing units on the basis of the first score. Therefore, compared with the first score, the adjusted first score is more reasonable, and further makes the ranking of the first housing unit determined based on the adjusted first score more reasonable in the housing unit information display order, which is beneficial to the full display of the housing unit information of different target housing units.

[0073] Regarding step S120, as another possible implementation manner, it may include steps S1231 to S1234 as shown in Figure 4 the following.

[0074] S1231. Determine the first coefficient according to the user interaction information of the first housing unit.

[0075] The implementation manner of step S1231 can refer to the description of step S1211. For the sake of brevity, it will not be elaborated here.

[0076] S1232. Calculate the similarity between the feature vectors of each second housing unit in m second housing units and the feature vector of the first housing unit.

[0077] The implementation of step S1232 can refer to the description of step S1221. For the sake of brevity, it will not be elaborated here.

[0078] S1233. Calculate the average value of the m similarities.

[0079] The implementation of step S1233 can refer to the description of step S1222. For the sake of brevity, it will not be elaborated here.

[0080] S1234. Multiply the weighted sum of the first score of the first housing source and the average value by the first coefficient to obtain the adjusted first score of the first housing source.

[0081] In one example, the adjusted first score score is calculated by the following formula: score = α × [(1 - β) × ctr(d) - β × s(d)], where α is the first coefficient, ctr(d) is the first score of a first housing source d, s(d) is the average value of the m similarities corresponding to a first housing source d, and 1 - β and -β are the weights respectively. The content related to β can refer to the above description. For the sake of brevity, it will not be elaborated here.

[0082] For the housing source information display method in the above implementation manner, the adjusted first score comprehensively considers the user interaction information of the first housing source and the feature vectors of m second housing sources on the basis of the first score, realizes a comprehensive adjustment of the first score, makes the ranking of the first housing source determined based on the adjusted first score more reasonable in the housing source information display order, and is beneficial to the full display of the housing source information of different target housing sources.

[0083] In some implementation manners of the present disclosure, before step S120, steps S150 and S160 as shown may further be included; correspondingly, step S120 may include step S1241, and step S130 may include step S131. Figure 5 As shown, step S150. Determine a target ranking in the housing source information display order.

[0084] The target ranking may be an empty ranking, that is, the target housing source located at this ranking has not been determined yet.

[0085] In one example, a series of empty rankings are pre-generated, and then, in the order of the rankings, the target housing sources located at each ranking are determined in turn. Among them, the target ranking is a ranking selected in the order of the rankings. The rankings before the target ranking have all determined the corresponding target housing sources, and the target ranking and the rankings after the target ranking have not determined the corresponding target housing sources yet.

[0086] In one example, a series of empty rankings are pre-generated, and then, in the order of the rankings, the target housing sources located at each ranking are determined in turn. Among them, the target ranking is a ranking selected in the order of the rankings. The rankings before the target ranking have all determined the corresponding target housing sources, and the target ranking and the rankings after the target ranking have not determined the corresponding target housing sources yet.

[0087] S160. During the process of determining the target housing unit located at the target ranking, determine whether the n second housing units meet the target business rules, where n is a positive integer.

[0088] Exemplarily, the size relationship between n and m is not limited. n can be a fixed value or can vary according to the target business rules.

[0089] The target business rules can be the preset business rules that take effect among multiple preset business rules, and the preset business rules can be set according to actual needs. The preset business rules that take effect can be set according to actual needs. For example, it can be one of the multiple preset business rules, or two, multiple, or even all of the multiple preset business rules. When there are multiple target business rules, it is determined that the n second housing units meet the target business rules when all multiple target business rules are met, and it is determined that the n second housing units do not meet the target business rules when any one of the target business rules is not met. When there is 1 target business rule, it is determined that the n second housing units meet the target business rules when the target business rule is met, and it is determined that the n second housing units do not meet the target business rules when the target business rule is not met.

[0090] One of the multiple preset business rules can be sequentially set to the effective state and the remaining preset business rules can be set to the ineffective state according to the priorities of the multiple preset business rules. In one example, the services include ordinary house rental, apartment rental, and worry-free house rental. Different services correspond to different target housing units. The first preset business rule is that among the second housing units ranked in the top 5, at least 1 target housing unit of each of the three services needs to be included. The second preset business rule is that among the second housing units ranked in the top 10, at least 3 target housing units under the worry-free house rental service need to be included. The third preset business rule is that among the second housing units ranked in the top 20, at least 3 target housing units under the apartment rental service need to be included. Then, the first preset business rule can be first set to the effective state and the second preset business rule and the third business rule can be set to the ineffective state. When the first preset business rule is met, the second preset business rule can be then set to the effective state and the first preset business rule and the third business rule can be set to the ineffective state. When the second preset business rule is met, the third preset business rule can be then set to the effective state and the first preset business rule and the second business rule can be set to the ineffective state. In this way, it is ensured that the multiple preset business rules accurately participate in the method at different stages. In this example, the n second housing units are all the second housing units for which the ranking has been determined.

[0091] S1241. When the n second housing units do not meet the target business rules, for each first housing unit among the multiple first housing units, adjust the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit to obtain the adjusted first score of the first housing unit.

[0092] The content related to adjusting the first score of the first housing source can be referred to the above description. For the sake of brevity, it will not be elaborated here.

[0093] S131. Based on the adjusted first score, determine a first housing source at the target ranking from multiple first housing sources.

[0094] Exemplarily, a first housing source with the largest adjusted first score among multiple first housing sources can be used as the first housing source at the target ranking.

[0095] In the housing source information display method of the above embodiment, in the process of determining a target housing source at the target ranking, first determine whether n second housing sources meet the target business rule, and when the n second housing sources do not meet the target business rule, for each first housing source among multiple first housing sources, adjust the first score of the first housing source based on the feature vector information and / or the user interaction information of the first housing source to obtain the adjusted first score of the first housing source, and based on the adjusted first score, determine a first housing source at the target ranking from multiple first housing sources. Thus, by introducing the target business rule, it is realized that the adjusted first scores of all first housing sources are not calculated separately in the process of determining the target housing source at each ranking, which can reduce the calculation amount, save the time required for sorting, and at the same time make the sorting result meet the actual business requirements.

[0096] In some embodiments of the present disclosure, after step S160, it may further include: when the n second housing sources meet the target business rule, determine a first housing source at the target ranking from multiple first housing sources based on the first score of the first housing source.

[0097] Exemplarily, a first housing source with the largest first score among multiple first housing sources can be used as the first housing source at the target ranking.

[0098] In the housing source information display method of the above embodiment, when the n second housing sources meet the target business rule, it is not necessary to calculate the adjusted first scores of each first housing source, and a first housing source at the target ranking can be directly determined from multiple first housing sources based on the first score of the first housing source, so as to reduce the calculation amount and save the time required for sorting.

[0099] In some embodiments of the present disclosure, the housing source information display method may further include: in the case where there is no second housing source, determine the rankings of a preset number of target housing sources in the housing source information display order based on the first score of the target housing source.

[0100] The preset number can be set according to actual needs. For example, it can be 3.

[0101] In one example, when there is no second listing (e.g., at the beginning of the sorting), based on the order of the first scores from large to small, a preset number of target listings with the largest first scores among multiple target listings are selected as target listings corresponding to the front preset number of rankings.

[0102] The housing information display method of the above embodiment, when there is no second housing source, directly determines a preset number of rankings based on the first score, which is conducive to the smooth execution of the method and ensures the universality of the method.

[0103] In some embodiments of the present disclosure, before step S110, the following may also be included: Figure 6 Steps S170 to S190 are shown.

[0104] S170: In response to the display of house information triggered by the user, obtain a user portrait and a second score of each of the multiple houses.

[0105] Exemplarily, when a user initiates a search or recommendation for housing information, it can be detected that the user triggers the display of housing information.

[0106] The second score can be the click-through rate, the number of business opportunities, or other values related to the target property.

[0107] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0108] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0109] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0110] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0111] Meanwhile, it can be understood that the data involved in the technical solution of the present disclosure (including but not limited to the data itself, the acquisition or use of data) should comply with the requirements of corresponding laws, regulations and related provisions.

[0112] S180. For each of the multiple housing units, adjust the second score of the housing unit based on the user profile to obtain the adjusted second score of the housing unit.

[0113] Exemplarily, the user profile includes the probability that the user prefers each of the multiple housing units. Further, step S180 may specifically be: for each of the multiple housing units of each of the multiple services, multiply the second score of the housing unit by the probability that the user prefers the housing unit to obtain the adjusted second score of the housing unit. It can be understood that if only the second scores of the housing units are used to display the housing unit information in descending order, then the housing units with low second scores are hardly shown. However, after comprehensively considering the second scores of the housing units and the user preferences by multiplication, if the second score of a housing unit is very low but the probability that the user prefers the housing unit is very high, then the calculated adjusted second score will increase much more than the second score, so that the housing units with very low second scores have a greater probability of being shown; similarly, if only the second scores are used to display the housing unit information in descending order, then the housing units with high second scores will be shown almost every time. However, after comprehensively considering the second scores of the housing units and the user preferences by multiplication, if the second score of a housing unit is very high but the probability that the user prefers the housing unit is very low, then the calculated adjusted second score will decrease much more than the second score, thereby reducing the display probability of the housing units with very high second scores and providing more display opportunities for other housing units.

[0114] S190. Determine the target housing unit from the multiple housing units based on the adjusted second score of the housing unit.

[0115] Exemplarily, in the case where there are multiple service types, for each of the multiple services, determine the multiple housing units with the largest adjusted second score under the service, and then use the housing units determined from the multiple services as the target housing units, so as to achieve multi-channel recall and enable the obtained multiple target housing units to cover multiple services.

[0116] The housing unit information display method of the above embodiment adjusts the second score of the housing unit based on the user profile, so that the obtained adjusted second score can comprehensively represent the second score of the housing unit and the matching degree with the user profile. Further, while the target housing unit determined based on the adjusted second score meets the user's needs, the display needs of different housing units are also taken into account.

[0117] Please combine Figure 7, in one example, both the first score and the second score are click-through rates. Further, the method for displaying housing information may include the following steps S201 to S219. The content related to steps S201 to S219 may refer to the description of the above embodiments. For the sake of brevity, it will not be elaborated here.

[0118] In step S201, in response to the display of housing information triggered by the user, obtain the user portrait and the click-through rate of each housing unit among multiple housing units.

[0119] In step S202, for each housing unit among the multiple housing units, adjust the click-through rate of the housing unit based on the user portrait to obtain the first adjusted click-through rate of the housing unit.

[0120] In step S203, for each service among multiple services, determine multiple housing units with the highest first adjusted click-through rate under the service, and then use the housing units determined from the multiple services as target housing units.

[0121] In step S204, generate a series of empty rankings, which are used to form the display order of housing information.

[0122] In step S205, use the 3 target housing units with the highest click-through rate among the multiple target housing units as the target housing units corresponding to rankings 1 to 3 in the display order of housing information respectively.

[0123] In step S206, based on the order of the rankings, determine the target ranking, that is, an empty ranking adjacent to the ranking corresponding to the target housing unit that has been determined, such as ranking 4.

[0124] In step S207, determine whether the target housing unit with the determined ranking meets the target service rule. If so, proceed to step S208; otherwise, proceed to step S209.

[0125] In step S208, when the target housing unit with the determined ranking meets the target service rule, use the target housing unit with the highest click-through rate among the multiple target housing units whose rankings have not been determined as the target housing unit at the target ranking.

[0126] In step S209, when the target housing unit with the determined ranking does not meet the target service rule, for each target housing unit among the multiple target housing units whose rankings have not been determined, adjust the click-through rate of the target housing unit based on the feature vector information (i.e., the feature vector of the target housing unit and the feature vectors of the 3 target housing units with the latest determined rankings) and / or the user interaction information of the target housing unit to obtain the second adjusted click-through rate of the target housing unit.

[0127] In step S210, one target housing unit with the largest second adjusted click-through rate among multiple target housing units whose rankings have not been determined is used as the target housing unit at the target ranking.

[0128] In step S211, it is determined whether the ranking traversal is completed. If so, step S212 is entered; if not, step S206 is entered.

[0129] In step S212, based on the housing unit information display order, the housing unit information of multiple target housing units is displayed.

[0130] Based on any of the above embodiments, the present disclosure also provides a housing unit information display device.

[0131] Figure 8 It is a structural schematic block diagram of a housing unit information display device according to an embodiment of the present disclosure.

[0132] As Figure 8 shown, the housing unit information display device includes: An acquisition module 110, configured to acquire a first score of a target housing unit, and acquire user interaction information of the target housing unit and / or a feature vector of the target housing unit; An adjustment module 120, configured to adjust the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit to obtain an adjusted first score of the first housing unit, where the feature vector information includes a feature vector of the first housing unit and feature vectors of m second housing units, the first housing unit is a target housing unit whose ranking in the housing unit information display order has not been determined, the second housing unit is a target housing unit whose ranking in the housing unit information display order has been determined, and m is a positive integer; A determination module 130, configured to determine the ranking of the first housing unit in the housing unit information display order based on the adjusted first score; A display module 140, configured to display the housing unit information of multiple target housing units based on the housing unit information display order.

[0133] The above housing unit information display device may be in the form of computer software, and each module of the above housing unit information display device may be implemented by a computer software module.

[0134] In some embodiments of the present disclosure, the adjustment module 120 is configured to: determine a first coefficient according to the user interaction information of the first housing unit; and adjust the first score of the first housing unit based on the first coefficient to obtain an adjusted first score of the first housing unit.

[0135] In some embodiments of the present disclosure, the adjustment module 120 is configured to: determine a preset value corresponding to the user interaction information of the first housing unit based on the mapping relationship between the keywords in the user interaction information and the preset values; and adjust the preset coefficient based on the preset value corresponding to the user interaction information of the first housing unit to obtain a first coefficient.

[0136] In some embodiments of the present disclosure, the adjustment module 120 is configured to: multiply the first score of the first housing unit by the first coefficient to obtain an adjusted first score of the first housing unit.

[0137] In some embodiments of the present disclosure, the adjustment module 120 is configured to: calculate the similarity between the feature vectors of each of the m second housing units and the feature vector of the first housing unit; calculate the average value of the m similarities; and adjust the first score of the first housing unit based on the average value to obtain an adjusted first score of the first housing unit.

[0138] In some embodiments of the present disclosure, the adjustment module 120 is configured to: perform a weighted sum of the first score of the first housing unit and the average value to obtain an adjusted first score of the first housing unit.

[0139] In some embodiments of the present disclosure, the adjustment module 120 is configured to: determine the first coefficient according to the user interaction information of the first housing unit; calculate the similarity between the feature vectors of each of the m second housing units and the feature vector of the first housing unit; calculate the average value of the m similarities; and multiply the weighted sum of the first score of the first housing unit and the average value by the first coefficient to obtain an adjusted first score of the first housing unit.

[0140] In some embodiments of the present disclosure, the housing unit information display device further includes: a second determination module, configured to determine a target ranking in the housing unit information display order; a judgment module, configured to judge whether the n second housing units meet the target business rules during the process of determining the target housing unit located at the target ranking, where n is a positive integer. Correspondingly, the adjustment module 120 is further configured to: in the case that the n second housing units do not meet the target business rules, for each of the multiple first housing units, adjust the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit to obtain an adjusted first score of the first housing unit; the determination module 130 is further configured to: determine a first housing unit located at the target ranking from the multiple first housing units based on the adjusted first score.

[0141] In some embodiments of the present disclosure, the housing unit information display device further includes: a third determination module, configured to, in the case that the n second housing units meet the target business rules, determine a first housing unit located at the target ranking from the multiple first housing units based on the first score of the first housing unit.

[0142] In some embodiments of the present disclosure, the housing information display device further includes: a fourth determination module, configured to determine the ranking of a preset number of target housing in the housing information display order based on the first score of the target housing when there is no second housing.

[0143] In some embodiments of the present disclosure, the housing information display device further includes: a second acquisition module, configured to acquire a user portrait and the second score of each housing among a plurality of housings in response to the housing information display triggered by the user; a second adjustment module, configured to adjust the second score of each housing among the plurality of housings based on the user portrait to obtain the adjusted second score of the housing; and a fifth determination module, configured to determine a target housing from the plurality of housings based on the adjusted second score of the housing.

[0144] The implementation processes of the functions and roles of each module in the above device are specifically described in the implementation processes of the corresponding steps in the above method, and will not be elaborated here.

[0145] The execution subject of the housing information display method in the specific embodiments of the present disclosure may be an electronic device such as a server, a mobile phone, a computer, etc.

[0146] Therefore, based on any of the above embodiments, the present disclosure further provides an electronic device, which can execute the housing information display method of any of the above embodiments described in the present disclosure.

[0147] Figure 9 It is a structural schematic diagram of an electronic device 1000 according to an embodiment of the present disclosure.

[0148] The hardware structure of the electronic device 1000 can be implemented using a bus architecture. The bus architecture can include any number of interconnected buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 1100 connects various circuits including one or more processors 1200, a memory 1300, and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripheral devices, voltage regulators, power management circuits, external antennas, etc.

[0149] The bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Component (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only one connection line is used in this figure, but it does not mean that there is only one bus or one type of bus.

[0150] The present disclosure also provides a readable storage medium storing a computer program which, when executed by a processor, is used to implement the above method. The "readable storage medium" may be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples of the readable storage medium include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer diskette case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM), etc.

[0151] The present disclosure also provides a computer program product. The method of the present disclosure can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed, the processes or functions of the present disclosure are executed in whole or in part.

[0152] The computer program or instructions can be stored in a readable storage medium, or transmitted from one readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired or wireless means. The readable storage medium can be any available medium that can be accessed or a data storage device such as a server or data center integrating one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it can also be an optical medium, such as a digital video disc; or it can be a semiconductor medium, such as a solid state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile types of storage media.

[0153] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0154] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the present disclosure. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0155] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0157] In the description of this specification, the descriptions referring to terms such as "one embodiment / way", "some embodiments / ways", "example", "specific example", or "some examples", etc. mean that the specific features, structures, or characteristics described in connection with the embodiment / way or example are included in at least one embodiment / way or example of the present disclosure. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment / way or example. Moreover, the specific features, structures, or characteristics described can be combined in a suitable manner in any one or more embodiments / ways or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments / ways or examples described in this specification and the features of different embodiments / ways or examples.

[0158] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0159] Those skilled in the art should understand that the above-described embodiments are merely for clearly illustrating the present disclosure and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications can be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A method for displaying housing source information, characterized in that Including: Obtain a first score of a target housing unit, and obtain user interaction information of the target housing unit and / or a feature vector of the target housing unit; Based on the feature vector information and / or the user interaction information of the first housing unit, adjust the first score of the first housing unit to obtain an adjusted first score of the first housing unit, where the feature vector information includes the feature vector of the first housing unit and the feature vectors of m second housing units, the first housing unit is a target housing unit whose ranking in the housing unit information display order has not been determined, the second housing unit is a target housing unit whose ranking in the housing unit information display order has been determined, and m is a positive integer; Based on the adjusted first score, determine the ranking of the first housing unit in the housing unit information display order; and Based on the housing unit information display order, display the housing unit information of multiple target housing units.

2. The housing source information display method according to claim 1, wherein Based on the feature vector information and / or the user interaction information of the first housing unit, adjusting the first score of the first housing unit to obtain an adjusted first score of the first housing unit includes: Determine a first coefficient according to the user interaction information of the first housing unit; and Based on the first coefficient, adjust the first score of the first housing unit to obtain an adjusted first score of the first housing unit.

3. The method for displaying housing source information according to claim 2, wherein Determining a first coefficient according to the user interaction information of the first housing unit includes: Based on the mapping relationship between keywords in the user interaction information and preset values, determine the preset value corresponding to the user interaction information of the first housing unit; and Based on the preset value corresponding to the user interaction information of the first housing unit, adjust a preset coefficient to obtain the first coefficient.

4. The housing source information display method according to claim 2, characterized in that Based on the first coefficient, adjusting the first score of the first housing unit to obtain an adjusted first score of the first housing unit includes: Multiply the first score of the first housing unit by the first coefficient to obtain an adjusted first score of the first housing unit.

5. The method for displaying housing source information according to claim 1, characterized in that, Based on the feature vector information and / or the user interaction information of the first housing unit, adjusting the first score of the first housing unit to obtain an adjusted first score of the first housing unit includes: Calculate the similarity between the feature vector of each second housing unit among the m second housing units and the feature vector of the first housing unit; Calculate the mean value of the m similarities; and Based on the mean value, adjust the first score of the first housing unit to obtain an adjusted first score of the first housing unit.

6. The method for displaying housing source information according to claim 5, wherein, Based on the mean value, adjusting the first score of the first housing unit to obtain an adjusted first score of the first housing unit includes: Perform weighted summation on the first score of the first housing unit and the mean value to obtain an adjusted first score of the first housing unit.

7. The housing source information display method according to claim 1, wherein Based on the feature vector information and / or the user interaction information of the first housing unit, adjusting the first score of the first housing unit to obtain an adjusted first score of the first housing unit includes: Determine a first coefficient according to the user interaction information of the first housing unit; Calculate the similarity between the feature vector of each second housing unit among the m second housing units and the feature vector of the first housing unit; Calculate the mean value of the m similarities; and Multiply the weighted sum of the first score of the first housing unit and the mean value by the first coefficient to obtain the adjusted first score of the first housing unit.

8. The housing source information display method according to claim 1, characterized in that, Before adjusting the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit, it further includes: Determine a target ranking in the housing unit information display order; During the process of determining the target housing unit located at the target ranking, determine whether the n second housing units meet the target business rules, where n is a positive integer; Adjusting the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit includes: In the case where the n second housing units do not meet the target business rules, for each first housing unit among the multiple first housing units, adjust the first score of the first housing unit based on the feature vector information and / or the user interaction information of the first housing unit to obtain the adjusted first score of the first housing unit; Determining the ranking of the first housing unit in the housing unit information display order based on the adjusted first score includes: Based on the adjusted first score, determine a first housing unit located at the target ranking from the multiple first housing units.

9. An electronic device, characterized in that, It includes: A memory that stores execution instructions; And A processor that executes the execution instructions stored in the memory, enabling the processor to execute the housing unit information display method according to any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the housing unit information display method according to any one of claims 1 to 8.

Images