Space content recommendation method and device, equipment and storage medium
By constructing and processing the interactive data matrix between users and spatial content, using the LSTM model to extract feature vectors and calculate dot product for sorting recommendations, the problem of cumbersome recommendation process of existing spatial content is solved, and efficient and reliable automated recommendations are achieved.
Patent Information
- Application Number
- CN202411908753.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-04-25
AI Technical Summary
The process of recommending content in existing spaces is cumbersome, resulting in inefficiency and susceptible to manual intervention.
By obtaining the park information and building information of the office space, integrating it into spatial content, obtaining the interactive data between users and spatial content, building an interaction matrix and decomposing it into user feature matrix and spatial content feature matrix, using the LSTM model to process the feature matrix, calculate the dot product of user feature vectors and spatial content feature vectors, and sorting and recommendations.
It realizes automated recommendations, reduces recommendation time, improves efficiency, and improves the reliability of recommendation results, avoiding the impact of manual intervention.
Smart Images
Figure CN119884509A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the fields of information technology and recommendation technology, and in particular to a spatial content recommendation method, device, equipment and storage medium. Background Art
[0002] Space content refers to the content of the office space. Through a comprehensive understanding and in-depth analysis of space content, users can more accurately evaluate the pros and cons of different office spaces and choose the location that best suits their development needs. An ideal office space can not only enhance the corporate image, but also promote employee work efficiency, optimize business processes, and even have a positive impact on attracting talents and partners.
[0003] However, the existing spatial content recommendation process is cumbersome and not conducive to improving the efficiency of spatial content recommendation. The reason is that the existing technology mainly adopts manual recommendation to recommend spatial content, which consumes a lot of human resources and time resources, increases the recommendation time of spatial content, and is easily affected by manual intervention. Therefore, it is not conducive to improving the efficiency of spatial content recommendation. Summary of the invention
[0004] The present invention provides a spatial content recommendation method, device, computer equipment and storage medium to solve the technical problem that the existing spatial content recommendation process is cumbersome and is not conducive to improving the spatial content recommendation efficiency.
[0005] In a first aspect, a spatial content recommendation method is provided, comprising: Obtaining the park information, building information, floor information, housing type and lease type of the office space, and integrating the park information, building information, floor information, housing type and lease type of the office space to obtain space content; Acquiring interaction data between the user and the space content; Constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; The user feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix; Acquire the enterprise data of the user, acquire the feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain the spatial content feature vector; The dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each of the spatial contents is sorted, and the spatial contents in the top M positions are selected as the recommendation results for the user.
[0006] Furthermore, the acquiring of interaction data between the user and the space content includes: Display the content of the space and read the preset collection instructions; The collection instruction is executed to collect interaction data between the user and the space content.
[0007] Furthermore, constructing an interaction matrix according to the interaction data and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix includes: Read the singular value decomposition algorithm in the preset file; Using the singular value decomposition algorithm, the interaction matrix is decomposed into a user feature matrix and a spatial content feature matrix.
[0008] Further, the using of the LSTM model to process the user feature matrix to obtain a feature vector corresponding to the user feature matrix, selecting the feature vector corresponding to the user feature matrix as the user feature vector, and using the LSTM model to process the space content feature matrix to obtain a feature vector corresponding to the space content feature matrix, includes: Inputting the user feature matrix and the spatial content feature matrix into a preset LSTM model; The user feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix.
[0009] Further, the acquiring of the enterprise data of the user, acquiring a feature vector corresponding to the enterprise data, and concatenating the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain a spatial content feature vector includes: Acquire the industrial and commercial data, judicial data, and business data submitted by the user, combine the industrial and commercial data, judicial data, and business data into the enterprise data of the user, extract keywords and tags from the enterprise data, perform feature extraction on the keywords and tags, and obtain feature vectors of the keywords and feature vectors of the tags; The feature vector of the keyword and the feature vector of the label are concatenated to obtain the feature vector corresponding to the enterprise data, and the feature vector corresponding to the enterprise data and the feature vector corresponding to the spatial content feature matrix are concatenated to obtain the spatial content feature vector.
[0010] Further, the calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each of the spatial contents, and selecting the spatial contents in the top M positions as the recommendation results for the user, includes: Calculating a dot product between the user feature vector and the spatial content feature vector, and selecting the dot product as a recommendation score for the spatial content; The recommendation scores of each of the space contents are ranked in descending order, and the top 10 space contents are selected as the recommendation results for the user.
[0011] Furthermore, after calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each spatial content, and selecting the spatial content in the top M positions as the recommendation result for the user, the spatial content recommendation method includes: Obtain a recommendation interface for the user, and display the recommendation result on the recommendation interface.
[0012] In a second aspect, a spatial content recommendation device is provided, comprising: The first acquisition module is used to acquire the park information, building information, floor information, house type and lease type of the office space, and integrate the park information, building information, floor information, house type and lease type of the office space to obtain the space content; A second acquisition module, used to acquire interaction data between the user and the space content; A decomposition module, used for constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; A processing module, used to process the user feature matrix using an LSTM model to obtain a feature vector corresponding to the user feature matrix, select the feature vector corresponding to the user feature matrix as the user feature vector, and process the space content feature matrix using the LSTM model to obtain a feature vector corresponding to the space content feature matrix; A third acquisition module is used to acquire the enterprise data of the user, acquire a feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain a spatial content feature vector; The recommendation module is used to calculate the dot product of the user feature vector and the spatial content feature vector, select the dot product as the recommendation score of the spatial content, sort the recommendation score of each spatial content, and select the spatial content in the top M positions as the recommendation result for the user.
[0013] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned spatial content recommendation method when executing the computer program.
[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned spatial content recommendation method are implemented.
[0015] The present application provides a spatial content recommendation method, device, computer equipment and storage medium, which obtain the park information, building information, floor information, house type and rental type of the office space, integrate the park information, building information, floor information, house type and rental type of the office space to obtain the spatial content; obtain the interaction data between the user and the spatial content; construct an interaction matrix according to the interaction data, and decompose the interaction matrix into a user feature matrix and a spatial content feature matrix; use the LSTM model to process the user feature matrix to obtain the feature vector corresponding to the user feature matrix, select the feature vector corresponding to the user feature matrix as the user feature vector, use the LSTM model to process the spatial content feature matrix to obtain the feature vector corresponding to the spatial content feature matrix; obtain the enterprise data of the user, obtain the feature vector corresponding to the enterprise data, and decompose the feature vector corresponding to the enterprise data into the feature vector corresponding to the enterprise data. The feature vector of the user and the feature vector corresponding to the spatial content feature matrix are concatenated to obtain the spatial content feature vector; the dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each spatial content is sorted, and the spatial content in the top M positions is selected as the recommendation result for the user. The beneficial effects are in two aspects. On the one hand, the dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each spatial content is sorted, and the spatial content in the top M positions is selected as the recommendation result for the user. Since no manual recommendation is required, the recommendation time of the spatial content is reduced, which is conducive to improving the recommendation efficiency of the spatial content. On the other hand, since the automatic recommendation will not be affected by manual intervention, it is conducive to improving the reliability of the recommendation results. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0017] Figure 1 is a schematic diagram of an application environment of a spatial content recommendation method according to an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of a spatial content recommendation method provided by an embodiment of the present invention; Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S23; Figure 4 yes Figure 2 A schematic flow chart of a specific implementation of step S25; Figure 5 yes Figure 2 A schematic flow chart of a specific implementation of step S26; Figure 6 is a structural diagram of a spatial content recommendation device in one embodiment of the present invention; Figure 7 It is a structural diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] See also Figure 1 , Figure 1 is a schematic diagram of an application environment of a spatial content recommendation method according to an embodiment of the present invention. The spatial content recommendation method provided by the embodiment of the present invention can be applied in Figure 1 In an application environment, a client communicates with a server through a network.
[0020] The server obtains the park information, building information, floor information, house type and lease type of the office space through the client, and integrates the park information, building information, floor information, house type and lease type of the office space to obtain the space content; Acquiring interaction data between the user and the space content; Constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; The user feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix; Acquire the enterprise data of the user, acquire the feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain the spatial content feature vector; The dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each of the spatial contents is sorted, and the spatial contents in the top M positions are selected as the recommendation results for the user.
[0021] In the scheme implemented by the above-mentioned spatial content recommendation method, device, equipment and medium, the beneficial effects are in two aspects. On the one hand, the dot product of the user feature vector and the spatial content feature vector is calculated, and the dot product is selected as the recommendation score of the spatial content. The recommendation score of each spatial content is sorted, and the spatial content in the top M positions is selected as the recommendation result for the user. Since no manual recommendation is required, the recommendation time of the spatial content is reduced, which is conducive to improving the recommendation efficiency of the spatial content. On the other hand, since the recommendation is automatic, it will not be affected by manual intervention, which is conducive to improving the reliability of the recommendation results.
[0022] The device running the client is referred to as a client device.
[0023] The device running the server is referred to as the server device.
[0024] Among them, client devices include but are not limited to smartphones, personal computers, Internet of Vehicles terminals, tablets and portable wearable devices.
[0025] The server device may be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments. Figure 2 , Figure 2 A schematic flow chart of a spatial content recommendation method provided by an embodiment of the present invention includes the following steps: S21, obtaining park information, building information, floor information, housing type, and rental type of the office space, and integrating the park information, building information, floor information, housing type, and rental type of the office space to obtain space content; Exemplarily, the park information, building information, floor information, housing type and rental type of the office space are obtained, and the park information, building information, floor information, housing type and rental type of the office space are integrated to obtain space content, including: Connect to a database, obtain real estate information from the database, obtain park information, building information, floor information, house type and rental type of the office space from the real estate information, integrate the park information, building information, floor information, house type and rental type of the office space to obtain space content.
[0026] Among them, integrating the park information, building information, floor information, house type and rental type of different office spaces can obtain different space contents.
[0027] For the sake of illustration, an example is given below: For example, there are multiple office spaces, and the multiple office spaces are office space 1, office space 2, and office space 3.
[0028] Integrate the park information, building information, floor information, house type, and rental type of office space 1 to obtain space content 1; Integrate the park information, building information, floor information, house type, and rental type of office space 2 to obtain space content 2; The park information, building information, floor information, house type and rental type of office space 3 are integrated to obtain space content 3.
[0029] Spatial content 1, spatial content 2, and spatial content 3 are different spatial contents.
[0030] S22, obtaining interaction data between the user and the space content; Wherein, the acquiring of interaction data between the user and the space content includes: Display the content of the space and read the preset collection instructions; The collection instruction is executed to collect interaction data between the user and the space content.
[0031] S23, constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; Among them, the user feature matrix is the user's feature matrix.
[0032] Among them, the spatial content feature matrix is the feature matrix of the spatial content.
[0033] Among them, the interaction matrix is decomposed into a user feature matrix and a spatial content feature matrix. This decomposition can reveal the potential structure and pattern in the interaction matrix. The user feature matrix captures the important features of the rows of the interaction matrix, and the spatial content feature matrix captures the important features of the columns of the interaction matrix. Through the user feature matrix and the spatial content feature matrix, the correlation and regularity in the interaction matrix can be understood.
[0034] Exemplarily, the rows of the interaction matrix represent the users, the columns of the interaction matrix represent the spatial contents, and the elements of the interaction matrix represent the user's ratings, likes, and reading dwell time for the spatial contents.
[0035] Exemplarily, the size of the interaction matrix R is m×n, where m is the total number of users, indicating that there are m users, and n is the total number of spatial contents, indicating that there are n spatial contents. The interaction matrix R is decomposed into the product of two matrices P and Q, namely:
[0036] Among them, P is an m×k matrix, representing the user feature matrix; Q is an n×k matrix, representing the spatial content feature matrix; k is a dimensional parameter much smaller than m and n, representing the number of potential features. represents the transposed matrix of Q. represents the transposed matrix, The product of can approximately reconstruct the original interaction matrix R.
[0037] Among them, decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix can significantly reduce the dimension of the interaction matrix, thereby reducing the amount of data in the interaction matrix. Since the amount of processed data is reduced, the processing time will also be reduced, which is conducive to improving processing efficiency.
[0038] S24, using the LSTM model to process the user feature matrix to obtain a feature vector corresponding to the user feature matrix, selecting the feature vector corresponding to the user feature matrix as the user feature vector, and using the LSTM model to process the space content feature matrix to obtain a feature vector corresponding to the space content feature matrix; Among them, the user feature vector is the feature vector of the user.
[0039] The Chinese name of the LSTM model is Long Short-Term Memory Network, and the English name of the LSTM model is Long Short-Term Memory. The LSTM model can selectively retain or forget information, thereby effectively capturing long-term dependencies in sequence data.
[0040] The method of using the LSTM model to process the user feature matrix to obtain a feature vector corresponding to the user feature matrix, selecting the feature vector corresponding to the user feature matrix as the user feature vector, and using the LSTM model to process the spatial content feature matrix to obtain a feature vector corresponding to the spatial content feature matrix includes: Inputting the user feature matrix and the spatial content feature matrix into a preset LSTM model; The user feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix.
[0041] S25, obtaining the enterprise data of the user, obtaining a feature vector corresponding to the enterprise data, and concatenating the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain a spatial content feature vector; Among them, the spatial content feature vector is the feature vector of the spatial content.
[0042] S26, calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each of the spatial contents, and selecting the spatial contents in the top M positions as the recommendation results for the user.
[0043] Among them, the user feature vector represents the characteristics of the user in terms of preference and behavior, and the space content feature vector represents the characteristics of the space content in terms of attributes and themes.
[0044] The dot product of the user feature vector and the spatial content feature vector is a scalar value, and the size of the dot product depends on the direction and length of the user feature vector and the spatial content feature vector.
[0045] If the user feature vector and the spatial content feature vector have the same or similar directions and their lengths increase, the dot product between the user feature vector and the spatial content feature vector will also increase, indicating that the degree of match between the user and the item is improved. The dot product is selected as the recommendation score of the spatial content. At this time, the recommendation score will also increase.
[0046] On the contrary, if the directional difference between the user feature vector and the spatial content feature vector increases, or the length decreases, the dot product between the user feature vector and the spatial content feature vector will also decrease, which means that the degree of match between the user and the spatial content decreases. The dot product is selected as the recommendation score of the spatial content. At this time, the recommendation score will also decrease.
[0047] Therefore, using the dot product of the user feature vector and the content feature vector as the recommendation score is an intuitive and effective approach, because this approach utilizes the geometric relationship in the vector space to capture the potential connection between users and items. It is not only simple to calculate, but also can reflect the complex relationship between users and spatial content, which is conducive to significantly improving the recommendation effect.
[0048] In addition, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each spatial content, and selecting the spatial content in the top M positions as the recommendation result for the user can greatly reduce the recommendation time of the spatial content and help improve the recommendation efficiency.
[0049] Wherein, M is a positive integer. Preferably, M is 10.
[0050] For the sake of illustration, an example is given below: For example, there are 50 space contents, and the recommendation score of each space content is sorted from large to small, and the space contents ranked 1 to 10 are selected as the recommendation results of the user.
[0051] For the sake of illustration, an example is given below: For example, there are 500 space contents, and the recommendation score of each space content is sorted from large to small, and the space contents ranked 1 to 10 are selected as the recommendation results for the user.
[0052] Among them, the space contents ranked 1st to 10th are selected as the recommendation results for the user, so that the user can select the office space according to the recommendation results. In this way, the user does not need to blindly search and filter the space contents in massive information, thereby saving the user's time and energy, and enabling the user to quickly find an office space that meets the budget and geographical location.
[0053] Wherein, after calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each spatial content, and selecting the spatial content in the top M positions as the recommendation result for the user, the spatial content recommendation method includes: Obtain a recommendation interface for the user, and display the recommendation result on the recommendation interface.
[0054] The recommendation results are displayed on the recommendation interface. This display method can fully utilize the interactivity of the recommendation interface, allowing users to browse the recommendation results intuitively, thereby improving the fluency and convenience of user experience.
[0055] In the embodiments of the present invention, the beneficial effects lie in two aspects. On the one hand, the dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each spatial content is sorted, and the spatial contents in the top M positions are selected as the recommendation results for the user. Since no manual recommendation is required, the recommendation time of the spatial content is reduced, which is conducive to improving the recommendation efficiency of the spatial content. On the other hand, since the automatic recommendation will not be affected by manual intervention, it is conducive to improving the reliability of the recommendation results.
[0056] See also Figure 3 , Figure 3 yes Figure 2 A specific implementation flow diagram of step S23 is described in detail as follows: S31, reading the singular value decomposition algorithm in the preset file; Among them, the singular value decomposition algorithm can not only achieve effective data compression, but also remove noise while retaining important information, thereby improving the efficiency and accuracy of data processing.
[0057] S32, using the singular value decomposition algorithm, decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix.
[0058] In the embodiment of the present invention, the interaction matrix is decomposed using a singular value decomposition algorithm, which can effectively reduce the dimension of the high-dimensional interaction matrix to a low-dimensional space, thereby simplifying calculations and reducing storage requirements.
[0059] See also Figure 4 , Figure 4 yes Figure 2 A specific implementation flow diagram of step S25 is described in detail as follows: S41, obtaining the industrial and commercial data, judicial data, and business data submitted by the user, combining the industrial and commercial data, judicial data, and business data into the enterprise data of the user, extracting keywords and tags from the enterprise data, performing feature extraction on the keywords and tags, and obtaining feature vectors of the keywords and the tags; S42, concatenating the feature vector of the keyword and the feature vector of the label to obtain the feature vector corresponding to the enterprise data, and concatenating the feature vector corresponding to the enterprise data and the feature vector corresponding to the spatial content feature matrix to obtain the spatial content feature vector.
[0060] In an embodiment of the present invention, the feature vector corresponding to the enterprise data and the feature vector corresponding to the spatial content feature matrix are concatenated to obtain a spatial content feature vector. Since the spatial content feature vector combines the feature vector corresponding to the enterprise data and the feature vector corresponding to the spatial content feature matrix, the spatial content feature vector is a more comprehensive and detailed data description, which can significantly improve the representation capability of the spatial content feature vector.
[0061] See also Figure 5 , Figure 5 yes Figure 2 A specific implementation flow diagram of step S26 is described in detail as follows: S51, calculating the dot product of the user feature vector and the spatial content feature vector, and selecting the dot product as the recommendation score of the spatial content; S52, sorting the recommendation score of each of the space contents in descending order, and selecting the top 10 space contents as the recommendation results for the user.
[0062] In the embodiment of the present invention, the recommendation score of each of the spatial contents is sorted in descending order, and the top 10 spatial contents are selected as the recommendation results for the user. Since no manual recommendation is required, the recommendation time of the spatial contents is reduced, which is conducive to improving the recommendation efficiency of the spatial contents.
[0063] See also Figure 6 , Figure 6 is a schematic diagram of a structure of a spatial content recommendation device in one embodiment of the present invention. Figure 6 As shown, the spatial content recommendation device includes a first acquisition module 101, a second acquisition module 102, a decomposition module 103, a processing module 104, a third acquisition module 105, and a recommendation module 106. The functional modules are described in detail as follows: The first acquisition module 101 is used to acquire the park information, building information, floor information, housing type and rental type of the office space, and integrate the park information, building information, floor information, housing type and rental type of the office space to obtain space content; A second acquisition module 102, used to acquire interaction data between the user and the space content; A decomposition module 103, configured to construct an interaction matrix according to the interaction data, and decompose the interaction matrix into a user feature matrix and a spatial content feature matrix; The processing module 104 is used to process the user feature matrix using the LSTM model to obtain a feature vector corresponding to the user feature matrix, select the feature vector corresponding to the user feature matrix as the user feature vector, and process the space content feature matrix using the LSTM model to obtain a feature vector corresponding to the space content feature matrix; The third acquisition module 105 is used to acquire the enterprise data of the user, acquire the feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain the spatial content feature vector; The recommendation module 106 is used to calculate the dot product of the user feature vector and the spatial content feature vector, select the dot product as the recommendation score of the spatial content, sort the recommendation score of each of the spatial contents, and select the spatial contents in the top M positions as the recommendation results for the user.
[0064] In the embodiment of the present invention, the beneficial effects lie in two aspects. On the one hand, the dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each spatial content is sorted, and the spatial contents in the top M positions are selected as the recommendation results for the user. Since no manual recommendation is required, the recommendation time of the spatial content is reduced, which is conducive to improving the recommendation efficiency of the spatial content. On the other hand, since the automatic recommendation will not be affected by manual intervention, it is conducive to improving the reliability of the recommendation results.
[0065] The specific definition of the spatial content recommendation device can refer to the definition of the spatial content recommendation method above, which will not be repeated here.
[0066] Each module in the above-mentioned spatial content recommendation device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0067] See also Figure 7 , Figure 7 1 is another structural diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device is a server device or a client device. The internal structure diagram thereof can be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external device. When the computer program is executed by the processor, the functions or steps of a spatial content recommendation method can be implemented.
[0068] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor.
[0069] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description of the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.
[0070] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), and a network processor (NP); it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.
[0071] The above description and the accompanying drawings sufficiently illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods and products disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.
[0072] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0073] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices and equipment) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some sub-samples can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.
[0074] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
Claims
1. A spatial content recommendation method, characterized in that: include: Obtaining the park information, building information, floor information, housing type and lease type of the office space, and integrating the park information, building information, floor information, housing type and lease type of the office space to obtain space content; Acquiring interaction data between the user and the space content; Constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; The user feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix; Acquire the enterprise data of the user, acquire the feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain the spatial content feature vector; The dot product of the user feature vector and the spatial content feature vector is calculated, the dot product is selected as the recommendation score of the spatial content, the recommendation score of each of the spatial contents is sorted, and the spatial contents in the top M positions are selected as the recommendation results for the user.
2. The spatial content recommendation method according to claim 1, characterized in that: The acquiring of interaction data between the user and the space content includes: Display the content of the space and read the preset collection instructions; The collection instruction is executed to collect interaction data between the user and the space content.
3. The spatial content recommendation method according to claim 1, characterized in that: The step of constructing an interaction matrix according to the interaction data and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix includes: Read the singular value decomposition algorithm in the preset file; The interaction matrix is decomposed into a user feature matrix and a spatial content feature matrix using the singular value decomposition algorithm.
4. The spatial content recommendation method according to claim 1, characterized in that: The using of the LSTM model to process the user feature matrix to obtain a feature vector corresponding to the user feature matrix, selecting the feature vector corresponding to the user feature matrix as the user feature vector, and using the LSTM model to process the space content feature matrix to obtain a feature vector corresponding to the space content feature matrix, includes: Inputting the user feature matrix and the spatial content feature matrix into a preset LSTM model; The user feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the user feature matrix, the feature vector corresponding to the user feature matrix is selected as the user feature vector, and the spatial content feature matrix is processed by using the LSTM model to obtain a feature vector corresponding to the spatial content feature matrix.
5. The spatial content recommendation method according to claim 1, characterized in that: The step of obtaining the enterprise data of the user, obtaining a feature vector corresponding to the enterprise data, and concatenating the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain a spatial content feature vector includes: Acquire the industrial and commercial data, judicial data, and business data submitted by the user, combine the industrial and commercial data, judicial data, and business data into the enterprise data of the user, extract keywords and tags from the enterprise data, perform feature extraction on the keywords and tags, and obtain feature vectors of the keywords and feature vectors of the tags; The feature vector of the keyword and the feature vector of the label are concatenated to obtain the feature vector corresponding to the enterprise data, and the feature vector corresponding to the enterprise data and the feature vector corresponding to the spatial content feature matrix are concatenated to obtain the spatial content feature vector.
6. The spatial content recommendation method according to claim 1, characterized in that: The step of calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each spatial content, and selecting the spatial content in the top M positions as the recommendation result for the user includes: Calculating a dot product between the user feature vector and the spatial content feature vector, and selecting the dot product as a recommendation score for the spatial content; The recommendation scores of each of the space contents are ranked in descending order, and the top 10 space contents are selected as the recommendation results for the user.
7. The spatial content recommendation method according to claim 1, characterized in that: After calculating the dot product of the user feature vector and the spatial content feature vector, selecting the dot product as the recommendation score of the spatial content, sorting the recommendation score of each spatial content, and selecting the spatial content in the top M positions as the recommendation result for the user, the spatial content recommendation method includes: Obtain a recommendation interface for the user, and display the recommendation result on the recommendation interface.
8. A spatial content recommendation device, characterized in that: include: The first acquisition module is used to acquire the park information, building information, floor information, house type and lease type of the office space, and integrate the park information, building information, floor information, house type and lease type of the office space to obtain the space content; A second acquisition module, used to acquire interaction data between the user and the space content; A decomposition module, used for constructing an interaction matrix according to the interaction data, and decomposing the interaction matrix into a user feature matrix and a spatial content feature matrix; A processing module, used to process the user feature matrix using an LSTM model to obtain a feature vector corresponding to the user feature matrix, select the feature vector corresponding to the user feature matrix as the user feature vector, and process the space content feature matrix using the LSTM model to obtain a feature vector corresponding to the space content feature matrix; A third acquisition module is used to acquire the enterprise data of the user, acquire a feature vector corresponding to the enterprise data, and concatenate the feature vector corresponding to the enterprise data with the feature vector corresponding to the spatial content feature matrix to obtain a spatial content feature vector; The recommendation module is used to calculate the dot product of the user feature vector and the spatial content feature vector, select the dot product as the recommendation score of the spatial content, sort the recommendation score of each spatial content, and select the spatial content in the top M positions as the recommendation result for the user.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the spatial content recommendation method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the spatial content recommendation method according to any one of claims 1 to 7 are implemented.