CN110309379B - Product recommendation method, device, equipment and computer readable storage medium - Google Patents
Product recommendation method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110309379B CN110309379B CN201910433256.4A CN201910433256A CN110309379B CN 110309379 B CN110309379 B CN 110309379B CN 201910433256 A CN201910433256 A CN 201910433256A CN 110309379 B CN110309379 B CN 110309379B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- sample
- cluster
- physique
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the field of data analysis, and provides a product recommendation method, a device, equipment and a computer readable storage medium, wherein the method comprises the following steps: when receiving user build data acquired and sent by a shared weighing scale, sending a corresponding terminal binding request to the shared weighing scale so that the shared weighing scale can display the terminal binding request; if a terminal binding instruction sent by a user terminal based on the terminal binding request is received within a preset time, binding the user terminal with the user physique data; extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset clustering rule so as to determine a target crowd; and acquiring high-frequency product information corresponding to the target crowd, and pushing the high-frequency product information to the user terminal. The invention realizes personalized information push and is beneficial to improving the suitability between the recommended product and the individual attribute of the user.
Description
Technical Field
The present invention relates to the field of data analysis, and in particular, to a product recommendation method, apparatus, device, and computer readable storage medium.
Background
With the continuous development of society, a shared weighing scale is started to appear on the market, and the shared weighing scale is placed in public areas such as a pharmacy, a mall, a hotel and the like by a merchant for use by users. When a user needs to detect the weight of the user through the shared weighing scale, the user can acquire a weight detection result by scanning a two-dimensional code or binding a social account number and a mobile phone number through the mobile terminal after the user gets on the weighing scale; meanwhile, the merchant can push relevant advertisement information (such as health insurance product information) to the mobile terminal of the user, so that the business promotion information is pushed. However, the "wide spread network" type propaganda popularization behavior is to push relative product information to all users, the suitability between the recommended product information and individual attributes of the users is poor, and the recommended effect is quite unsatisfactory.
Disclosure of Invention
The invention mainly aims to provide a product recommending method, device, equipment and a computer readable storage medium, and aims to solve the technical problem that in the existing product recommending process, the suitability of individual attributes of a product and a user is poor.
In order to achieve the above object, an embodiment of the present invention provides a product recommendation method, including:
when receiving user physique data acquired and sent by a shared weighing scale, sending a corresponding terminal binding request to the shared weighing scale according to the user physique data so that the shared weighing scale can display the terminal binding request;
if a terminal binding instruction sent by a user terminal based on the terminal binding request is received within a preset time, binding the user terminal with the user physical data according to the terminal binding instruction;
extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset clustering rule so as to determine a target crowd in the preset sample crowd according to an analysis result;
and acquiring high-frequency product information corresponding to the target crowd, and pushing the high-frequency product information to the user terminal.
In addition, in order to achieve the above object, an embodiment of the present invention further provides a product recommendation device, including:
the request sending module is used for sending a corresponding terminal binding request to the shared weighing scale according to the user physique data when receiving the user physique data acquired and sent by the shared weighing scale, so that the shared weighing scale can display the terminal binding request;
The data binding module is used for binding the user terminal with the user physique data according to the terminal binding instruction if the terminal binding instruction sent by the user terminal based on the terminal binding request is received within the preset time;
the cluster analysis module is used for extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset cluster rule so as to determine a target crowd in the preset sample crowd according to an analysis result;
and the information pushing module is used for acquiring the high-frequency product information corresponding to the target crowd and pushing the high-frequency product information to the user terminal.
In addition, in order to achieve the above object, an embodiment of the present invention further provides a product recommendation device, which includes a processor, a memory, and a product recommendation program stored on the memory and executable by the processor, wherein the product recommendation program, when executed by the processor, implements the steps of the product recommendation method as described above.
In addition, in order to achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium having a product recommendation program stored thereon, wherein the product recommendation program, when executed by a processor, implements the steps of the product recommendation method as described above.
The invention provides a product recommending method, a device, equipment and a computer readable storage medium, which are used for acquiring physical data of a user through a shared weighing scale, analyzing and determining a target group to which the user belongs by taking the physical data of the user as a starting point, recommending corresponding product information to the user according to product purchasing characteristics corresponding to the target group, realizing personalized information push, being beneficial to improving the suitability between recommended products and individual attributes of the user, further improving the product popularization effect, enriching new customer acquisition scenes of a service staff, and helping to solve new customer acquisition demands of the service.
Drawings
FIG. 1 is a schematic hardware structure of a product recommendation device according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a product recommendation method according to the present invention;
FIG. 3 is a flowchart of a second embodiment of the product recommendation method of the present invention;
fig. 4 is a schematic functional block diagram of a first embodiment of the product recommendation device according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The product recommending method related to the embodiment of the invention is mainly applied to product recommending equipment, and the product recommending equipment can be equipment with data processing functions such as a server, a personal computer (personal computer, PC), a notebook computer and the like.
Referring to fig. 1, fig. 1 is a schematic hardware structure of a product recommendation device according to an embodiment of the present invention. In an embodiment of the present invention, the product recommendation device may include a processor 1001 (e.g., central processing unit Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communications between these components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM) or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may alternatively be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration shown in fig. 1 is not limiting of the invention and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
With continued reference to FIG. 1, the memory 1005 of FIG. 1, which is a computer readable storage medium, may include an operating system, a network communication module, and a product recommendation program. In fig. 1, a network communication module may be used to connect to a database for data communication therewith; and the processor 1001 may call the product recommendation program stored in the memory 1005 and execute the product recommendation method provided by the embodiment of the present invention.
The embodiment of the invention provides a product recommendation method.
Referring to fig. 2, fig. 2 is a flow chart of a first embodiment of a product recommendation method according to the present invention.
In this embodiment, the product recommendation method includes the following steps:
step S10, when receiving user physique data acquired and sent by a shared weighing scale, sending a corresponding terminal binding request to the shared weighing scale according to the user physique data so that the shared weighing scale can display the terminal binding request;
with the continuous development of society, a shared weighing scale is started to appear on the market, and the shared weighing scale is placed in public areas such as a pharmacy, a mall, a hotel and the like by a merchant for use by users. When a user needs to detect the weight of the user through the shared weighing scale, the user can acquire a weight detection result by scanning a two-dimensional code or binding a social account number and a mobile phone number through the mobile terminal after the user gets on the weighing scale; meanwhile, the merchant can push relevant advertisement information (such as health insurance product information) to the mobile terminal of the user, so that the business promotion information is pushed. However, the "wide spread network" type propaganda popularization behavior is to push relative product information to all users, the suitability between the recommended product information and individual attributes of the users is poor, and the recommended effect is quite unsatisfactory. In this regard, the present embodiment provides a product recommendation method, which is described in terms of recommendation of health risk products: when a user uses the shared weighing scale, when physical data of the user is obtained through the shared weighing scale, a target health group to which the user belongs is determined according to physical data analysis of the user, and corresponding health risk product information is pushed to the user according to the target health group to which the user belongs, so that the use of the shared weighing scale is combined with the popularization flow of the health risk product, personalized information push is realized according to physical data of the user, the product popularization effect is improved, new customer acquisition scenes of a salesman are enriched, and new customer acquisition demands of a business are solved.
The product recommendation method in this embodiment is implemented by a product recommendation apparatus, which is described by taking a recommendation server as an example. The recommendation server in the embodiment is connected with the shared weighing scale network, and the recommendation server and the shared weighing scale network can realize data interaction; the shared weighing scale is placed in advance in public areas such as pharmacies, shops, hotels, and the like. When a certain user needs to measure own physical data, the user can stand on the detection area of the shared weighing scale; when the shared weighing scale detects that the detection area is standing, user physique data of the user are acquired, wherein the data types of the user physique data comprise, but are not limited to, weight, body fat rate, fat weight, skeletal muscle weight, muscle rate and the like; when the user physique data acquisition is completed, the shared weighing scale can send the user physique data to the recommendation server. Of course, in practice, the recommendation server may be simultaneously connected to two or more (more than two includes this number, and the same applies below) shared weighing scales in a network, and when sending the user physical data to the recommendation server, the shared weighing scales will also send their own device identification (such as the communication address, hardware number, current location information, etc. of the shared weighing scales) together in order to indicate the source of the user physical data. When receiving user build data collected and sent by the shared weighing scale, the recommendation server firstly sends a corresponding terminal binding request to the shared weighing scale according to the user build data in order to display the user build data to a user and conduct subsequent product recommendation operation, so that the shared weighing scale can display the terminal binding request. The terminal binding request can be in the form of a two-dimensional code, when a user scans the two-dimensional code through a user terminal (mobile phone or tablet computer and other equipment), the user can be considered to agree to bind the user physical data with the user terminal of the user, and a corresponding identity binding instruction is sent to a recommendation server through the user terminal; the terminal binding request can also be in the form of a verification code, when a user sends the verification code to a certain number through a user terminal, the user can be considered to agree to bind the user physical data with the user terminal of the user, and a corresponding identity binding instruction is sent to a recommendation server through the user terminal; of course the terminal binding request may also be of other forms.
Step S20, if a terminal binding instruction sent by a user terminal based on the terminal binding request is received within a preset time, binding the user terminal with the user physique data according to the terminal binding instruction;
in this embodiment, when the recommendation server receives an identity binding instruction sent by the user terminal based on the terminal binding request, it may be determined that the user agrees to bind the user build data with the user terminal of the recommendation server, and at this time, the recommendation server binds the user terminal with the user build data according to the identity binding instruction, and uses the user terminal as an object for pushing related information to the user subsequently, thereby enriching a new customer acquisition scenario and helping to solve a new customer acquisition requirement of a service. After binding the user terminal and the user physical data, the recommendation server also sends the user physical data obtained in step S10 to the user terminal, so that the user can know the physical condition of the user.
It should be noted that, in this embodiment, the recommendation server sends the user physical data to the user terminal that binds based on the terminal binding request; in practice, after the user uses the shared weighing scale, the user terminal of the user may not be subjected to related binding operation, and if a third person performs binding operation based on a terminal binding request displayed by the shared weighing scale through the third terminal, the third person may obtain user physique data of the previous user; in order to avoid the occurrence of the situation, the recommendation server sends a terminal binding request to the shared weighing scale, so that the method has certain timeliness; if a terminal binding instruction sent by the user terminal based on the terminal binding request is received in a preset time, the recommendation server binds the user terminal with the user physique data according to the terminal binding instruction; when the preset time is exceeded, the terminal binding request is invalid, and the user (or a third person) cannot perform binding operation through the terminal binding request. For example, when the terminal binding request is a two-dimensional code, the effective time of the two-dimensional code is 1 minute, if a user uses his mobile phone to scan the two-dimensional code within 1 minute, the mobile phone sends a corresponding terminal binding instruction to a recommendation server, and the recommendation server binds the mobile phone with user physique data according to terminal binding; after 1 minute, the two-dimensional code is invalid, and even if the recommendation server receives a terminal binding instruction sent by the user terminal based on the two-dimensional code, related binding operation cannot be performed, so that the situation that physical data of the user are acquired by other people is avoided to a certain extent, and the safety of the physical data of the user is protected.
Further, in this embodiment, if the recommendation server does not receive the terminal binding instruction sent by the user terminal based on the terminal binding request within the preset time, the user physical data will be deleted. By the mode, the storage of the user build data in the memory of the server can be avoided, the leakage of the user build data under the condition that the user is unaware can be avoided, and the memory of the server can be saved.
Still further, for the user physical data, the user physical data may also be used for business performance statistics, as it reflects to some extent the results of the business operator's exploitation of the business market. For example, a salesman may be associated with several shared weighing scales; when the shared weighing scale sends user physique data to the recommendation server, the shared weighing scale sends the self equipment identification together; when the recommendation server successfully binds the user with the user physique data, the recommendation server can consider that a potential user is acquired at the time, at the moment, the recommendation server can determine the business personnel to which the performance belongs according to the equipment identifier, and records the performance attribution as related data for carrying out other data settlement (such as salary calculation), and the method is beneficial to mobilizing and improving the enthusiasm of the business personnel through body weight scale exhibition.
Step S30, extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset cluster rule so as to determine a target crowd in the preset sample crowd according to an analysis result;
in this embodiment, after binding the user terminal and the user physique data, the recommendation server will analyze and determine the target group (i.e. the crowd with the same or similar physique) to which the user belongs according to the physique data of the user, and push the corresponding health risk product information to the user according to the target group to which the user belongs. In the process of determining the target group to which the user belongs, since the user physique data includes multiple types of data, and physique data among different healthy groups may have a more secret relation, in this embodiment, a cluster analysis manner may be adopted to determine target sample data in the same cluster (same kind) as the user physique data in the sample physique data of the sample crowd collected in advance, and the target crowd to which the target sample data in the same cluster belongs may be considered to belong to the same target group as the user.
Alternatively, the process of cluster analysis of the present embodiment may be implemented by Means of K-Means clustering (K-Means). For convenience of description, K in this embodiment is described by taking 2 as an example. The recommendation server can be connected with a preset database in a network, the preset database stores sample physique data of a plurality of sample crowds collected in advance, and for the sample physique data and the user physique data, the user physique data can be quantized into corresponding user coordinate sets according to a preset quantization rule, and the sample physique data is quantized into corresponding sample coordinate sets; of course, the sample set and the user coordinate set have the same coordinate dimensions, and may be "(body weight, body fat rate, fat weight, skeletal muscle weight, muscle rate)", for example, and the coordinate set dimensions may be set according to actual situations in actual references. When quantization is completed, the pushing server randomly selects two coordinate sets from the sample coordinate set and the user coordinate set to serve as initial clustering centers; wherein the number of initial cluster centers, i.e. the number of clusters of information (value of K) of the clustering process. In determining the initial cluster center, the initial distance of the set of coordinates of each initial cluster to each non-initial center will be calculated (this distance may be represented in a variety of ways, such as Euclidean distance, manhattan distance, chebyshev distance, etc.). When the initial distance between each initial clustering center and each non-initial center coordinate set is obtained, each non-initial center coordinate set takes the initial clustering center with a closer distance as a clustering target, so that the initial clustering coordinate set corresponding to each initial clustering center is determined, and at the moment, each initial clustering center and each corresponding initial clustering coordinate set form an initial clustering cluster, namely all coordinate sets are divided into two types. When the initial cluster is obtained, the recommendation server determines secondary cluster centers in each initial cluster through a certain election algorithm, wherein the election algorithm can be determined through a coordinate mean value calculation mode or a weighted mean value mode (namely, different weight values are assigned to different coordinate groups on the basis of the coordinate mean value, for example, the weight value of a user coordinate group is larger than the weight value of a sample coordinate group, so that the cluster centers are determined to be nearby the user coordinate group as much as possible). And for a secondary cluster center, it is slightly different from the initial cluster center, i.e. the secondary cluster center may be a virtual set of coordinates. In determining secondary cluster centers, secondary distances for each secondary cluster center and each non-secondary center coordinate set will be calculated separately (the calculation process is similar to the initial distance calculation and the distances are expressed in the same way). When the secondary distance is obtained, a secondary clustering coordinate set corresponding to each secondary clustering center can be determined according to the secondary distance, so that a secondary clustering cluster is obtained, namely, all the coordinate sets are divided into two types again. When the secondary cluster is obtained, the recommendation server compares the clustering condition of the secondary cluster with the clustering condition of the previous cluster (namely, the initial cluster) and judges whether the clustering condition and the clustering condition are consistent (namely, judges whether the two classification conditions are consistent or not). If the two clusters are consistent, the clustering convergence is considered, namely the clustering is completed, at the moment, the secondary cluster where the user coordinate set is located can be determined as a target cluster, the sample crowd corresponding to the target sample coordinate set (target sample data) included in the target physical cluster is the target crowd, and the target crowd can be considered as the crowd with similar physical state with the user; if the two clusters are inconsistent, the clustering can be considered as not converging, at the moment, iterative clustering is needed to be carried out on the secondary cluster again, the direct clustering converges (namely, the obtained iterative cluster is consistent with the coordinate component classification condition of the previous cluster), the specific iterative clustering process is similar to the secondary clustering process, and the detailed description is omitted.
Further, in this embodiment, for the user physical data obtained by the shared weighing scale in step S10 and the sample physical data stored in the preset database, the data types related to the two are not necessarily the same, and due to the functional limitation of the shared weighing scale, the data types of the user physical data may be less than the sample data, for example, the sample physical data includes skeletal muscle weight, and the user physical data does not include skeletal muscle weight; if the two data types are different, the accuracy of the analysis is reduced, and even the situation that the cluster analysis cannot be performed occurs. To avoid this problem, the present embodiment also performs normalization and type unification on the user physique data and the sample physique data when they are quantized. Specifically, the step of quantizing the user physique data into a corresponding user coordinate set and the step of quantizing the sample physique data into a corresponding sample coordinate set according to a preset quantization rule includes:
determining the data type included in the user physical data, and carrying out data filtering on the sample physical data according to the data type to obtain corresponding effective sample data;
When the recommendation server quantifies the coordinate set, firstly determining the data type included in the user physique data, and then carrying out data filtering operation on the sample physique data according to the data type of the user physique data, namely eliminating the data type not included in the user physique data in the sample physique data; for example, if skeletal muscle weight is not included in the user build data and skeletal muscle weight is included in the sample build data, the skeletal muscle weight in the sample build data may be filtered out, and subsequent operations may be performed without using the item of data, and the filtered sample build data may be referred to as valid sample data, where the valid sample data includes data types consistent with the user build data. Of course, in practice, the relevant staff or the user may specify the data type for analysis, and the recommendation server may perform data filtering on the user physical data and the sample physical data according to the specified data type.
Respectively ordering the user physique data and the effective sample data according to a preset ordering rule and the data type to obtain a corresponding user physique sequence and an effective sample sequence;
When the effective sample data is obtained, the recommendation server also sorts the user physique data and the effective sample data according to a certain sorting rule, so that the data values in the user physique data and the effective sample data are sorted according to a certain data type sequence, for example, the sorting rule is body weight, body fat rate, fat weight and muscle rate, and the recommendation server sorts the data values in the user physique data and the effective sample data according to the rules to obtain a corresponding user physique sequence and an effective sample sequence, so that the user physique sequence and the effective sample sequence are subjected to regular processing.
And obtaining a corresponding user coordinate set according to the user physique sequence and obtaining a corresponding sample coordinate set according to the effective sample sequence.
When the user physique sequence and the effective sample sequence are obtained, a corresponding user coordinate set can be obtained according to the user physique sequence, a corresponding sample coordinate set can be obtained according to the effective sample sequence, and the user coordinate set and the sample coordinate set are used for cluster analysis to determine a target crowd corresponding to a user (user physique data).
And S40, acquiring high-frequency product information corresponding to the target crowd, and pushing the high-frequency product information to the user terminal.
In this embodiment, when determining the target crowd, the recommendation server will acquire high-frequency product information corresponding to the target crowd. For example, taking health insurance products as an example, for the process of obtaining high-frequency health insurance products, health insurance purchase records of all target people in the target people can be obtained first, then a plurality of health insurance products with the largest number of purchases are determined according to the health insurance purchase records, and the plurality of health insurance products with the largest number of purchases can be regarded as high-frequency products corresponding to the target people, and related introduction information of the high-frequency products is high-frequency product information. When the high-frequency product information is obtained, the recommendation server can push the high-frequency product information to the user terminal so that the user can know the health insurance products purchased by the crowd with the same physical constitution at high frequency. Of course, in practice, the recommendation server may acquire the high-frequency product information of other dangerous types in addition to the health dangerous product, and push the high-frequency product information to the user terminal. The high-frequency product information may be transmitted to the user terminal together with the user physical data of the user. In addition, the pushed information may be set by a service person, for example, the recommendation server may first send a related information pushing task to a corresponding service terminal, the service person selects or makes related pushing information through the service terminal, and when the selection/making is completed, the information is pushed to the user terminal through the recommendation server.
Further, when the recommendation server obtains the user physical data of the user, the recommendation server can provide a data storage function for the user so as to keep the user physical data, and when the user needs to check, the recommendation server inquires through the user terminal; in the storage process, in order to protect the privacy of the user, a secret storage function can be provided for the user. In this embodiment, in order to improve storage security, the encryption operation may be performed by public-private key encryption, and specifically, the product recommendation method of this embodiment further includes:
when a data encryption instruction sent by the user terminal is received, extracting a data public key included in the data encryption instruction, wherein a data private key corresponding to the data public key is stored by the user terminal;
when a user needs to encrypt user physical data of a recommendation server, the user terminal can be operated to generate an asymmetric key pair, wherein the asymmetric key pair comprises a data public key and a data private key, and the data private key is stored locally in the user terminal; and then the user terminal generates a corresponding data encryption instruction according to the data public key and sends the data encryption instruction to the recommendation server. And the recommendation server can extract the data public key included in the data encryption instruction when receiving the data encryption instruction.
And encrypting and storing the user physical data based on the data public key.
When the recommendation server obtains the data public key, encrypting the user physical data based on the data public key, and storing the encrypted user physical data. At this time, since the data private key required for decrypting the user physical data is stored in the user terminal, even if the encrypted user physical data is acquired by a third party, the user physical data cannot be decrypted and the real data value of the user physical data cannot be obtained; thereby ensuring user privacy. If the user needs to inquire own physical data, a data inquiry instruction can be sent to the recommendation server through the user terminal, and the recommendation server returns the encrypted user physical data to the user terminal according to the data inquiry instruction; and the user terminal performs decryption operation through a local data private key when receiving the encrypted user physical data so as to allow the user to check the specific data value.
Still further, the user physical data in this embodiment is acquired and sent by the shared weighing scale, so that the recommendation server can also judge whether the use of the shared weighing scale is abnormal or not based on the data sending frequency of the shared weighing scale, and prompt related staff in time when the use is abnormal. Specifically, the product recommendation method of the embodiment further includes:
Counting the physical data transmission times of the shared weighing scale in a preset period, and judging whether the physical data transmission times are smaller than a preset flow threshold;
the recommendation server can regularly count the physical data transmission times of the shared weighing scale in a preset period at a certain fixed counting time point, for example, the physical data transmission times of the shared weighing scale in the last week are counted at 9 am of every monday; and then the recommendation server compares the physical data transmission times with a preset flow threshold value and judges whether the physical data transmission times are smaller than the preset flow threshold value.
And if the physical data sending times are smaller than the preset flow threshold, sending weight scale use abnormality information to a corresponding management end.
If the number of times of sending the physical data is smaller than a preset flow threshold, the shared weighing scale can be considered to have abnormal use, and at the moment, a recommendation server sends weighing scale abnormal use information to a corresponding management end so as to prompt related staff and conduct abnormality investigation; when the recommendation server sends the weight scale use abnormality information to the management end, the information can also comprise address information of the abnormal weight scale, related salesmen and other contents. Of course, there may be various situations when the shared weighing scale is abnormally used, for example, the software/hardware of the shared weighing scale may be faulty and cannot be used normally, or the shared weighing scale may be used for a small number of times (i.e. less passenger flow).
In this embodiment, when receiving user physique data collected and sent by a shared weighing scale, a corresponding terminal binding request is sent to the shared weighing scale according to the user physique data, so that the shared weighing scale can display the terminal binding request; if a terminal binding instruction sent by a user terminal based on the terminal binding request is received within a preset time, binding the user terminal with the user physical data according to the terminal binding instruction; extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset clustering rule so as to determine a target crowd in the preset sample crowd according to an analysis result; and acquiring high-frequency product information corresponding to the target crowd, and pushing the high-frequency product information to the user terminal. Through the mode, the embodiment obtains the physical data of the user through the shared weighing scale, then takes the physical data of the user as a starting point, analyzes and determines the target group to which the user belongs, recommends corresponding product information to the user according to the product purchasing characteristics corresponding to the target group, realizes personalized information push, is beneficial to improving the suitability between the recommended product and the individual attribute of the user, further improves the product popularization effect, simultaneously enriches the new customer acquisition scene of a service staff, and helps to solve the new customer acquisition demand of the service.
Referring to fig. 3, fig. 3 is a flow chart of a second embodiment of the product recommendation method according to the present invention.
Based on the embodiment shown in fig. 2, in this embodiment, the high-frequency product information includes a manual service link, and after step S40, the method further includes:
and step S50, when receiving a manual service request sent by the user terminal based on the manual service link, inquiring a corresponding manual customer service end according to the high-frequency product information, and sending corresponding service task information to the manual customer service end.
In this embodiment, in order to facilitate the user to consult, the high-frequency product information pushed by the recommendation server further includes a manual service link, considering that the user may have a question or interest after browsing the pushed information; after the user browses the pushed high-frequency product information through the user terminal, if manual consultation is needed to be carried out on the service personnel, the user terminal can click on the manual service link, so that a corresponding manual service request is triggered; and the user terminal sends the manual service request to the recommendation server according to the operation of the user. When receiving the manual service request, the recommendation server firstly inquires a corresponding manual customer service end (or a terminal of a service person responsible for sharing the weighing scale) according to the source of the user physique data, and sends corresponding service task information to the manual customer service end; the service task information can comprise an IP address, an account name, a telephone number and the like of the user terminal, so that customer service personnel can quickly contact with the user through the service terminal, manual service is provided for the user, the time spent by the user for requesting manual inquiry is reduced, the service experience of the user is improved, the time spent for internal task allocation and data transfer can be reduced, and the service processing efficiency is improved.
In addition, the embodiment of the invention also provides a product recommending device.
Referring to fig. 4, fig. 4 is a schematic functional block diagram of a first embodiment of a product recommendation device according to the present invention.
In this embodiment, the product recommendation device includes:
the request sending module 10 is configured to send a corresponding terminal binding request to the shared weighing scale according to user physique data when receiving the user physique data acquired and sent by the shared weighing scale, so that the shared weighing scale displays the terminal binding request;
the data binding module 20 is configured to bind the user terminal with the user physique data according to the terminal binding instruction if a terminal binding instruction sent by the user terminal based on the terminal binding request is received within a preset time;
the cluster analysis module 30 is configured to extract sample physique data of a preset sample crowd, and perform cluster analysis on the user physique data and the sample physique data based on a preset cluster rule, so as to determine a target crowd in the preset sample crowd according to an analysis result;
and the information pushing module 40 is configured to obtain high-frequency product information corresponding to the target crowd, and push the high-frequency product information to the user terminal.
Wherein, each virtual function module of the product recommendation device is stored in the memory 1005 of the product recommendation device shown in fig. 1, and is used for implementing all functions of the product recommendation program; the modules, when executed by the processor 1001, perform the functions associated with product recommendation.
Further, the product recommendation device further includes:
the public key extraction module is used for extracting a data public key included in the data encryption instruction when the data encryption instruction sent by the user terminal is received, wherein a data private key corresponding to the data public key is stored by the user terminal;
and the data encryption module is used for encrypting and storing the user physical data based on the data public key.
Further, the cluster analysis module 20 includes:
the coordinate set quantization unit is used for quantizing the user physique data into a corresponding user coordinate set and quantizing the sample physique data into a corresponding sample coordinate set according to a preset quantization rule;
the center selecting unit is used for randomly selecting more than two coordinate sets from the user coordinate set and the sample coordinate set as initial clustering centers, and respectively calculating the initial distances between each initial clustering center and each non-initial center coordinate set;
The primary clustering unit is used for determining initial clustering coordinate sets corresponding to the initial clustering centers according to initial distances between the initial clustering centers and the non-initial center coordinate sets, and obtaining initial clustering clusters according to the initial clustering centers and the initial clustering coordinate sets corresponding to the initial clustering centers;
the center election unit is used for determining secondary clustering centers in all initial clustering clusters based on a preset election algorithm and respectively calculating secondary distances between all initial clustering centers and all non-secondary center coordinate sets;
the secondary clustering unit is used for determining secondary clustering coordinate sets corresponding to the secondary clustering centers according to the secondary distances between the secondary clustering centers and the non-secondary center coordinate sets, and obtaining secondary clustering clusters according to the secondary clustering centers and the secondary clustering coordinate sets corresponding to the secondary clustering centers;
the cluster judgment unit is used for judging whether the clustering conditions of the coordinate sets of each secondary cluster and each initial cluster are consistent;
the target cluster determining unit is used for determining the secondary cluster where the user coordinate set is located as a target cluster if the user coordinate set is consistent with the target cluster; if the coordinate groups of the obtained iterative cluster are inconsistent with the coordinate groups of the previous cluster, carrying out iterative cluster on the secondary cluster until the obtained iterative cluster is consistent with the coordinate groups of the previous cluster, and determining the iterative cluster where the coordinate groups of the protected person are located as a target cluster;
The crowd determining unit is used for determining target crowd in the preset sample crowd according to the target sample coordinate set included in the target information cluster.
Further, the coordinate set quantization unit is specifically configured to:
determining the data type included in the user physical data, and carrying out data filtering on the sample physical data according to the data type to obtain corresponding effective sample data;
respectively ordering the user physique data and the effective sample data according to a preset ordering rule and the data type to obtain a corresponding user physique sequence and an effective sample sequence;
and obtaining a corresponding user coordinate set according to the user physique sequence and obtaining a corresponding sample coordinate set according to the effective sample sequence.
Further, the high-frequency product information includes a manual service link, and the product recommendation device further includes:
and the task sending module is used for inquiring the corresponding artificial customer service end according to the high-frequency product information when receiving the artificial service request sent by the user terminal based on the artificial service link and sending corresponding service task information to the artificial customer service end.
Further, the product recommendation device further includes:
The number counting module is used for counting the physical data transmission number of the shared weighing scale in a preset period and judging whether the physical data transmission number is smaller than a preset flow threshold;
and the information sending module is used for sending the abnormal use information of the weighing scale to the corresponding management end if the physical data sending times are smaller than the preset flow threshold.
Further, the product recommendation device further includes:
and the data deleting module is used for deleting the user physical data if the terminal binding instruction sent by the user terminal based on the terminal binding request is not received within the preset time.
The function implementation of each module in the product recommendation device corresponds to each step in the method embodiment of the product recommendation device, and the function and implementation process of each module are not described in detail herein.
In addition, the embodiment of the invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention stores a product recommendation program, wherein the product recommendation program, when executed by a processor, implements the steps of the product recommendation method as described above.
The method implemented when the product recommendation program is executed may refer to various embodiments of the product recommendation method of the present invention, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. A product recommendation method, characterized in that the product recommendation method comprises:
when receiving user physique data acquired and sent by a shared weighing scale, sending a corresponding terminal binding request to the shared weighing scale according to the user physique data so that the shared weighing scale can display the terminal binding request;
if a terminal binding instruction sent by a user terminal based on the terminal binding request is received within a preset time, binding the user terminal with the user physical data according to the terminal binding instruction;
extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset clustering rule so as to determine a target crowd in the preset sample crowd according to an analysis result;
acquiring high-frequency product information corresponding to the target crowd, and pushing the high-frequency product information to the user terminal;
The step of performing cluster analysis on the user physique data and the sample physique data based on a preset cluster rule to determine a target crowd in the preset sample crowd according to an analysis result comprises the following steps:
quantizing the user physique data into a corresponding user coordinate set according to a preset quantization rule, and quantizing the sample physique data into a corresponding sample coordinate set;
randomly selecting more than two coordinate sets from the user coordinate set and the sample coordinate set as initial clustering centers, and respectively calculating initial distances between each initial clustering center and each non-initial center coordinate set;
determining initial cluster coordinate sets corresponding to the initial cluster centers according to initial distances between the initial cluster centers and the non-initial center coordinate sets, and obtaining initial cluster clusters according to the initial cluster centers and the initial cluster coordinate sets corresponding to the initial cluster centers;
determining secondary clustering centers in each initial clustering cluster based on a preset election algorithm, and respectively calculating secondary distances between each initial clustering center and each non-secondary center coordinate set;
determining secondary clustering coordinate sets corresponding to the secondary clustering centers according to the secondary distances between the secondary clustering centers and the non-secondary center coordinate sets, and obtaining secondary clustering clusters according to the secondary clustering centers and the secondary clustering coordinate sets corresponding to the secondary clustering centers;
Judging whether the clustering conditions of the coordinate sets of each secondary cluster and each initial cluster are consistent;
if the two clusters are consistent, determining the secondary cluster where the user coordinate set is located as a target cluster; if the two clusters are inconsistent, carrying out iterative clustering on the two clusters until the obtained iterative cluster is consistent with the coordinate component classification condition of the previous cluster, and determining the iterative cluster where the user coordinate group is located as a target cluster;
and determining a target crowd in the preset sample crowd according to a target sample coordinate set included in the target cluster.
2. The product recommendation method as recited in claim 1, further comprising:
when a data encryption instruction sent by the user terminal is received, extracting a data public key included in the data encryption instruction, wherein a data private key corresponding to the data public key is stored by the user terminal;
and encrypting and storing the user physical data based on the data public key.
3. The product recommendation method of claim 1, wherein the step of quantizing the user physique data into corresponding sets of user coordinates according to preset quantization rules and the step of quantizing the sample physique data into corresponding sets of sample coordinates comprises:
Determining the data type included in the user physical data, and carrying out data filtering on the sample physical data according to the data type to obtain corresponding effective sample data;
respectively ordering the user physique data and the effective sample data according to a preset ordering rule and the data type to obtain a corresponding user physique sequence and an effective sample sequence;
and obtaining a corresponding user coordinate set according to the user physique sequence and obtaining a corresponding sample coordinate set according to the effective sample sequence.
4. The product recommendation method according to claim 1, wherein the high frequency product information comprises a manual service link,
after the step of obtaining the high-frequency product information corresponding to the target crowd and pushing the high-frequency product information to the user terminal, the method further comprises the steps of:
and when receiving a manual service request sent by the user terminal based on the manual service link, inquiring a corresponding manual customer service end according to the high-frequency product information, and sending corresponding service task information to the manual customer service end.
5. The product recommendation method as recited in claim 1, further comprising:
Counting the physical data transmission times of the shared weighing scale in a preset period, and judging whether the physical data transmission times are smaller than a preset flow threshold;
and if the physical data sending times are smaller than the preset flow threshold, sending weight scale use abnormality information to a corresponding management end.
6. The product recommendation method according to any one of claims 1 to 5, wherein when receiving user build data collected and transmitted by a shared weighing scale, the step of transmitting a corresponding terminal binding request to the shared weighing scale according to the user build data, so that the shared weighing scale displays the terminal binding request, further comprises:
and if the terminal binding instruction sent by the user terminal based on the terminal binding request is not received within the preset time, deleting the user physical data.
7. A product recommendation device for use in the product recommendation method of any one of claims 1 to 6, characterized in that the product recommendation device comprises:
the request sending module is used for sending a corresponding terminal binding request to the shared weighing scale according to the user physique data when receiving the user physique data acquired and sent by the shared weighing scale, so that the shared weighing scale can display the terminal binding request;
The data binding module is used for binding the user terminal with the user physique data according to the terminal binding instruction if the terminal binding instruction sent by the user terminal based on the terminal binding request is received within the preset time;
the cluster analysis module is used for extracting sample physique data of a preset sample crowd, and carrying out cluster analysis on the user physique data and the sample physique data based on a preset cluster rule so as to determine a target crowd in the preset sample crowd according to an analysis result;
and the information pushing module is used for acquiring the high-frequency product information corresponding to the target crowd and pushing the high-frequency product information to the user terminal.
8. A product recommendation device, characterized in that it comprises a processor, a memory, and a product recommendation program stored on the memory and executable by the processor, wherein the product recommendation program, when executed by the processor, implements the steps of the product recommendation method according to any of claims 1 to 6.
9. A computer-readable storage medium, wherein a construction program is stored on the computer-readable storage medium, wherein the construction program, when executed by a processor, implements the steps of the product recommendation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433256.4A CN110309379B (en) | 2019-05-22 | 2019-05-22 | Product recommendation method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433256.4A CN110309379B (en) | 2019-05-22 | 2019-05-22 | Product recommendation method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110309379A CN110309379A (en) | 2019-10-08 |
| CN110309379B true CN110309379B (en) | 2023-07-25 |
Family
ID=68075450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910433256.4A Active CN110309379B (en) | 2019-05-22 | 2019-05-22 | Product recommendation method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309379B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111698332A (en) * | 2020-06-23 | 2020-09-22 | 深圳壹账通智能科技有限公司 | Method, device and equipment for distributing business objects and storage medium |
| CN111814903B (en) * | 2020-07-21 | 2022-04-01 | 上海数鸣人工智能科技有限公司 | Method for analyzing user sensitivity to marketing activities based on DPI clustering |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492194A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Products Show method, apparatus and storage medium |
| WO2019014971A1 (en) * | 2017-07-19 | 2019-01-24 | 深圳市天士网络科技有限公司 | Data processing method, measurement device and system server |
| WO2019061656A1 (en) * | 2017-09-30 | 2019-04-04 | 平安科技（深圳）有限公司 | Electronic apparatus, service place recommendation method based on lbs data, and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7743059B2 (en) * | 2007-03-30 | 2010-06-22 | Amazon Technologies, Inc. | Cluster-based management of collections of items |
-
2019
- 2019-05-22 CN CN201910433256.4A patent/CN110309379B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019014971A1 (en) * | 2017-07-19 | 2019-01-24 | 深圳市天士网络科技有限公司 | Data processing method, measurement device and system server |
| WO2019061656A1 (en) * | 2017-09-30 | 2019-04-04 | 平安科技（深圳）有限公司 | Electronic apparatus, service place recommendation method based on lbs data, and storage medium |
| CN108492194A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Products Show method, apparatus and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110309379A (en) | 2019-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9460475B2 (en) | Determining connectivity within a community | |
| CN108769024B (en) | Data acquisition method and multi-data operator negotiation service system | |
| US20140095308A1 (en) | Advertisement distribution apparatus and advertisement distribution method | |
| US20130036059A1 (en) | Electronic price-proposing system, electronic price-proposing device, and electronic price-proposing method | |
| CN110309379B (en) | Product recommendation method, device, equipment and computer readable storage medium | |
| US11593513B2 (en) | Information processing system, data provision system, and related method | |
| CN111598162A (en) | Cattle risk monitoring method, terminal equipment and storage medium | |
| CN111490995A (en) | Model training method and device for protecting privacy, data processing method and server | |
| KR101719198B1 (en) | Method for managing personal information and payment information in user terminal or device and recommendation system using the same | |
| KR100985949B1 (en) | System and method for providing product information service by mobile network system | |
| KR101827480B1 (en) | Apparatus and system for recommending products using user's mobile access log and method thereof | |
| CN110832489A (en) | Information processing apparatus, information processing system, information processing method, and program | |
| KR20090112049A (en) | Method for network-based on 3dimension virtual reality and system thereof | |
| CN105099993B (en) | A kind of data interactive method based on agent platform, device and system | |
| KR101437651B1 (en) | Method for processing membership according to affiliated store registration request of client and apparatus for the same and system for the same | |
| JP2013210933A (en) | Recommendation support method, recommendation support device and program | |
| CN110610380A (en) | User portrait acquisition method, device, equipment and computer readable storage medium | |
| CA3024718C (en) | Data exchange processing method, terminal, and system | |
| JP7083369B2 (en) | Attribute ratio estimation system | |
| WO2022185542A1 (en) | Server device, terminal, system, server control method, and storage medium | |
| EP1616234A1 (en) | A method in data transmission, a data transmission system, and a device | |
| CN106796689A (en) | Data interactive processing method, terminal and system | |
| JP6829176B2 (en) | Judgment device, judgment method and information provision system | |
| JP2020042332A (en) | Contents contact situation research system, contents contact situation research method, and program | |
| JP5951667B2 (en) | Server apparatus and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |