A data recommendation system and method

Abstract

This invention discloses a data recommendation system and method. The system includes: a wireless wearable EEG device for detecting and preprocessing EEG signals, generating EEG data and sending it to a mobile terminal; a mobile terminal for determining user operation data and sending it, along with the received EEG data, to a cloud data processing center; a cloud data processing center for retrieving historical user data based on the received user operation data and sending it, along with the received EEG data, to an intelligent recommendation server; and an intelligent recommendation server for performing clustering and collaborative filtering based on the received historical user data and EEG data, generating filtered data, performing an intersection operation, and obtaining multiple recommendation parameters which are then sent to the cloud. This application retrieves historical user data based on user operation data, performs clustering and collaborative filtering to find historical user data with high similarity to the current user, and constructs recommendation results for the current user based on this historical user data, thereby improving recommendation speed and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a data recommendation system and method. BACKGROUND

[0002] With the rapid development of the Internet, the number of network audio data is also increasing rapidly. For people who like to relax through audio data, this is both good news and bad news. The good news is that people can have more and more choices to choose audio data suitable for themselves, and the bad news is that they do not know how to choose audio data suitable for themselves from these massive audio data. Therefore, an intelligent audio data recommendation system based on personalization has emerged.

[0003] In the prior art, when data recommendation is performed, for example, in the patent with the patent number 201710379428.5, the brain relaxation degree of a user is obtained by processing the brain electrical signals of the user collected in real time, then a "user-music" evaluation matrix is obtained according to the historical evaluation data of the user on music, the brain relaxation degree of the user and the "user-music" evaluation matrix of the user are weighted and fused to obtain a music preference prediction score of the user, and finally the user is recommended by using a preset intelligent music recommendation algorithm according to the music preference prediction score of the user. Since the music preference prediction score is calculated according to the brain electrical signals in the prior art, the recommendation speed and accuracy are reduced due to the calculation according to the set formula without upgrading the device, and the formula involves multiple variables with variable factors. SUMMARY

[0004] The present application provides a data recommendation system and method. To have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This part is not a general review, nor does it determine the key / important elements or describe the protection scope of these embodiments. The only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, the present application provides a data recommendation system, which comprises:

[0006] a wireless wearable electroencephalogram device, a mobile terminal, a cloud data processing center, and an intelligent recommendation server;

[0007] The wireless wearable electroencephalogram device, the mobile terminal, the cloud data processing center, and the intelligent recommendation server are in communication connection;

[0008] The wireless wearable electroencephalogram device is used for detecting and preprocessing brain electrical signals, generating brain electrical data, and sending the brain electrical data to the mobile terminal;

[0009] A mobile terminal is configured to determine user operation data, and send received electroencephalogram data and the user operation data to a cloud data processing center.

[0010] The cloud data processing center is configured to retrieve historical user data according to the received user operation data, and send the to-be-processed user data to the intelligent recommendation server.

[0011] The intelligent recommendation server is configured to perform clustering and collaborative filtering according to the received historical user data and electroencephalogram data, generate filtered data, perform intersection operation based on the filtered data, generate a plurality of recommended working parameters, and send the recommended working parameters to the cloud data processing center.

[0012] Optionally, the cloud data processing center is further configured to construct a plurality of recommended results according to the received recommended working parameters, and send the recommended results to the mobile terminal.

[0013] The mobile terminal is further configured to display the received recommended results, and when a selection instruction for the recommended results is received, determine a target recommended result from the recommended results, and send the target recommended result to the wireless wearable electroencephalogram device.

[0014] The wireless wearable electroencephalogram device is further configured to play audio according to the received target recommended result.

[0015] Optionally, the wireless wearable electroencephalogram device comprises a perception component and a feedback component.

[0016] The perception component and the feedback component are in communication connection.

[0017] The perception component is configured to detect and preprocess electroencephalogram signals, generate electroencephalogram data, and send the electroencephalogram data to the mobile terminal when a communication connection is established with the mobile terminal.

[0018] The feedback component is configured to receive the target recommended result sent from the mobile terminal, and play audio based on the target recommended result.

[0019] Optionally, the perception component comprises an electroencephalogram electrode, a signal acquisition module, a computing processing module, and a wireless sending module.

[0020] The electroencephalogram electrode, the signal acquisition module, the computing processing module, and the wireless sending module are in electrical connection.

[0021] The electroencephalogram electrode and the signal acquisition module are configured to detect and acquire electroencephalogram signals.

[0022] The computing processing module is configured to perform decoding and encoding operations on the electroencephalogram signals to generate electroencephalogram data, and the wireless sending module is configured to send the electroencephalogram data to the mobile terminal.

[0023] Optionally, the feedback component comprises an audio playing module and a wireless receiving module; wherein,

[0024] The audio playing module and the wireless receiving module are electrically connected; wherein,

[0025] The wireless receiving module is configured to receive the target recommendation result sent by the mobile terminal;

[0026] The audio playing module is configured to play audio based on the target recommendation result.

[0027] Optionally, the user operation data is determined, and the received electroencephalogram data and the user operation data are sent to a cloud data processing center, comprising:

[0028] Upon receiving a user registration instruction, the personal basic information of the current user is obtained;

[0029] The user inputted working parameters are received;

[0030] When the recommendation strategy selected by the current user is a default recommendation strategy or a self-selected recommendation strategy, the personal basic information and the working parameters are displayed;

[0031] A parameter selection instruction for the displayed data is received, a plurality of target values are selected from the basic information and the working parameters based on the parameter selection instruction, and a recommendation algorithm parameter is generated;

[0032] The personal basic information, the working parameters, the recommendation algorithm parameter, and the received electroencephalogram data are sent to the cloud data processing center.

[0033] Optionally, the historical user data is retrieved according to the received user operation data, and the to-be-processed user data is sent to the intelligent recommendation server, comprising:

[0034] The received electroencephalogram data is saved, and the received personal basic information, working parameters, and recommendation algorithm parameter are also saved;

[0035] The historical user personal information, historical user working parameters, and historical user electroencephalogram data are obtained by searching in the database according to the selected label data in the recommendation algorithm parameter;

[0036] The real-time electroencephalogram data, historical user personal information, historical user working parameters, and historical user electroencephalogram data are combined to form to-be-processed user data;

[0037] The to-be-processed user data is sent to the intelligent recommendation server.

[0038] Optionally, the filtering data is generated by clustering and collaborative filtering according to the received historical user data and electroencephalogram data, comprising:

[0039] The K-means clustering algorithm is used to cluster the electroencephalogram data in the user data to be processed into three groups according to energy levels, and a plurality of clustering results are generated.

[0040] In the plurality of clustering results, the target clustering result to which the five electroencephalogram wave energies in the real-time electroencephalogram data belong is determined, and five clustering results are obtained.

[0041] The user with the highest number of registered usernames in the five clustering results is taken as the registered user space.

[0042] According to the recommendation algorithm parameters and the preset collaborative filtering algorithm, a plurality of first user data with the highest similarity are determined from the historical user data; and the plurality of first user data are determined as filtering data.

[0043] Optionally, an intersection operation is performed based on the filtering data to generate a plurality of recommended work parameters, including:

[0044] According to the registered usernames, a plurality of second user data are searched for in the registered user space.

[0045] The plurality of first user data and the plurality of second user data are subjected to an intersection operation to generate intersection user data.

[0046] The work parameters of the intersection user data are determined as the plurality of recommended work parameters.

[0047] In a second aspect, the embodiments of the present application provide a data recommendation method, which comprises:

[0048] The wireless wearable electroencephalogram device is used to detect and preprocess electroencephalogram signals, generate electroencephalogram data, and send the electroencephalogram data to a mobile terminal.

[0049] The mobile terminal is used to determine user operation data, and send the received electroencephalogram data and user operation data to a cloud data processing center.

[0050] The cloud data processing center is used to retrieve historical user data according to the received user operation data, and send the user data to be processed to the intelligent recommendation server.

[0051] The intelligent recommendation server is used to perform clustering and collaborative filtering according to the received historical user data and electroencephalogram data, generate filtering data, perform an intersection operation based on the filtering data, generate a plurality of recommended work parameters, and send the recommended work parameters to the cloud data processing center.

[0052] The technical scheme provided by the embodiments of the present application can include the following beneficial effects:

[0053] In the embodiment of the present application, first, the wireless wearable electroencephalogram device detects and preprocesses the electroencephalogram signal, generates electroencephalogram data and sends to the mobile terminal, then the mobile terminal determines the user operation data, and sends to the cloud data processing center together with the received electroencephalogram data, second, the cloud data processing center retrieves historical user data according to the received user operation data, and sends to the intelligent recommendation server together with the received electroencephalogram data, finally, the intelligent recommendation server clusters and collaborative filtering according to the received historical user data and electroencephalogram data, performs intersection operation after filtering data, obtains a plurality of recommended working parameters and sends to the cloud. According to the operation data of the user, the historical user data is clustered and collaborative filtered to find out the historical user data with the highest similarity to the current user, and the recommendation result is constructed for the current user through the historical user data, thereby improving the recommendation speed and accuracy.

[0054] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0055] The drawings incorporated into the specification and forming part thereof illustrate embodiments in accordance with the present application and, together with the specification, serve to explain the principles of the application.

[0056] Figure 1 is a system schematic diagram of a data recommendation system provided by an embodiment of the present application;

[0057] Figure 2 is a structure schematic diagram of a wireless wearable electroencephalogram device provided by an embodiment of the present application;

[0058] Figure 3 is a flow schematic diagram of a data recommendation method provided by an embodiment of the present application;

[0059] Figure 4 is a process schematic block diagram of a data recommendation process provided by an embodiment of the present application;

[0060] Figure 5 is a flow schematic block diagram of clustering and collaborative filtering provided by an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following description and drawings sufficiently illustrate specific embodiments of the present application to enable one skilled in the art to practice them.

[0062] It should be clear that the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0063] The following description refers to the accompanying drawings. Unless otherwise noted, same or similar components in different drawings have same or similar reference numerals. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of systems consistent with some aspects of the present application as detailed in the appended claims.

[0064] In the description of the present application, it should be understood that the terms "first", "second" and the like are used to describe various elements, but not to indicate or imply relative importance. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "a plurality of" means two or more. The "and / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after are in an "or" relationship.

[0065] The technical solution provided by the present application clusters and cooperatively filters historical user data according to user operation data to find the highest similarity historical user data with the current user, and constructs a recommendation result for the current user through the historical user data, thereby improving the recommendation speed and accuracy. For example, in the prior art, 100 monkeys are selected, and through the comparison in the early stage, it is found that A type monkeys eat I type bananas, and B type monkeys like to eat II bananas. A banana type formula can be developed as Y=A(X)+B(X), and the known formula can be used to recommend banana types to monkeys. The present application does not need to train in advance to obtain Y=A(X)+B(X), nor does it use similar formulas in the recommendation algorithm. Only when A monkey eats bananas, the present application will recommend the banana type that the monkey similar in age, gender, state, and physical signs (EEG) likes to eat to A monkey, and recommend the banana to A monkey. The following will be described in detail by exemplary embodiments.

[0066] Please refer to Figure 1 , Figure 1 is a system structure schematic diagram of a data recommendation system provided by an embodiment of the present application. The system comprises a wireless wearable EEG device 101, a mobile terminal 102, a cloud data processing center 103, and an intelligent recommendation server 104. The wireless wearable EEG device 101, the mobile terminal 102, the cloud data processing center 103, and the intelligent recommendation server 104 are in communication connection.

[0067] In the embodiment of the present application, the wireless wearable electroencephalogram device is used for detecting and preprocessing electroencephalogram signals, generating electroencephalogram data, and sending the data to a mobile terminal; the mobile terminal is used for determining user operation data and sending the received electroencephalogram data and user operation data to a cloud data processing center; the cloud data processing center is used for retrieving historical user data according to the received user operation data and sending the to-be-processed user data to an intelligent recommendation server; the intelligent recommendation server is used for clustering and collaborative filtering according to the received historical user data and electroencephalogram data, generating filtered data, performing intersection operation based on the filtered data, generating a plurality of recommended working parameters, and sending the parameters to the cloud data processing center.

[0068] Further, the cloud data processing center is also used for constructing a plurality of recommended results according to the received recommended working parameters and sending the results to the mobile terminal; the mobile terminal is also used for displaying the received plurality of recommended results and determining a target recommended result from the plurality of recommended results and sending the result to the wireless wearable electroencephalogram device when a selection instruction for the plurality of recommended results is received; the wireless wearable electroencephalogram device is also used for playing audio according to the received target recommended result.

[0069] In the embodiment of the present application, for example Figure 2 As shown in the figure, the wireless wearable electroencephalogram device 101 comprises a perception component 201 and a feedback component 201; wherein the perception component 201 and the feedback component 202 are communicatively connected.

[0070] Specifically, the perception component is used for detecting and preprocessing electroencephalogram signals, generating electroencephalogram data, and sending the data to a mobile terminal when a communication connection is established with the mobile terminal; the feedback component is used for receiving a target recommended result sent from the mobile terminal and playing audio based on the target recommended result.

[0071] In the embodiment of the present application, for example Figure 2 As shown in the figure, the perception component 201 comprises an electroencephalogram electrode 301, a signal acquisition module 302, a calculation processing module 303, and a wireless sending module 304; wherein the electroencephalogram electrode 301, the signal acquisition module 302, the calculation processing module 303, and the wireless sending module 304 are electrically connected.

[0072] Specifically, the electroencephalogram electrode and the signal acquisition module are used for detecting and acquiring electroencephalogram signals; the calculation processing module is used for decoding and encoding operation on the electroencephalogram signals to generate electroencephalogram data; and the wireless sending module is used for sending the electroencephalogram data to a mobile terminal.

[0073] In the embodiment of the present application, for example Figure 2 As shown in the figure, the feedback component 202 comprises an audio playing module 305 and a wireless receiving module 306; wherein the audio playing module 305 and the wireless receiving module 306 are electrically connected.

[0074] Specifically, the wireless receiving module is configured to receive a target recommendation result sent by the mobile terminal; and the audio playing module is configured to play audio based on the target recommendation result.

[0075] In the embodiments of the present application, when the user operation data is determined and the received electroencephalogram data and the user operation data are sent to the cloud data processing center, first, when the user registration instruction is received, the personal basic information of the current user is obtained, and then the plurality of working parameters input by the user are received. When the recommendation strategy selected by the current user is the default recommendation strategy or the self-selected recommendation strategy, the personal basic information and the plurality of working parameters are displayed. Then, the parameter selection instruction for the displayed data is received, and the plurality of target values are selected from the basic information and the plurality of working parameters based on the parameter selection instruction. The recommendation algorithm parameters are generated. Finally, the personal basic information, the plurality of working parameters, the recommendation algorithm parameters and the received electroencephalogram data are sent to the cloud data processing center.

[0076] In the embodiments of the present application, when the historical user data is retrieved according to the received user operation data, and the to-be-processed user data is sent to the intelligent recommendation server, first, the received electroencephalogram data is saved, and the received personal basic information, the plurality of working parameters and the recommendation algorithm parameters are saved. Then, the historical user personal information, the historical user working parameters and the historical user electroencephalogram data are obtained by searching in the database according to the selected label data in the recommendation algorithm parameters. Then, the real-time electroencephalogram data, the historical user personal information, the historical user working parameters and the historical user electroencephalogram data are combined to form the to-be-processed user data. Finally, the to-be-processed user data is sent to the intelligent recommendation server.

[0077] In the embodiments of the present application, when the filtering data is generated by clustering and collaborative filtering according to the received historical user data and the electroencephalogram data, first, the K-means clustering algorithm is used to cluster the electroencephalogram data in the to-be-processed user data into three groups according to the energy level, and a plurality of clustering results are generated. Then, the target clustering result to which the five kinds of electroencephalogram energy in the real-time electroencephalogram data belong is determined in the plurality of clustering results, and five clustering results are obtained. Then, the user whose registered username appears most frequently in the five clustering results is taken as a registered user space. Finally, according to the recommendation algorithm parameters and the preset collaborative filtering algorithm, a plurality of first user data with the highest similarity are determined from the historical user data; and the plurality of first user data are determined as the filtering data.

[0078] In the embodiment of the present application, when the intersection operation is performed based on the filtered data to generate the plurality of recommended work parameters, first, the plurality of sets of second user data are searched for in the registered user space according to the registered user name, then the intersection operation is performed on the plurality of sets of first user data and the plurality of sets of second user data to generate intersection user data, and finally the intersection user data is determined as the plurality of recommended work parameters.

[0079] In the embodiment of the present application, first, the wireless wearable electroencephalogram device detects and preprocesses the electroencephalogram signal to generate electroencephalogram data and sends the electroencephalogram data to the mobile terminal, then the mobile terminal determines user operation data and sends the received electroencephalogram data and the user operation data to the cloud data processing center, second, the cloud data processing center searches historical user data according to the received user operation data and sends the received electroencephalogram data and the historical user data to the intelligent recommendation server, and finally the intelligent recommendation server performs clustering and collaborative filtering on the received historical user data and the electroencephalogram data, performs intersection operation on the filtered data to obtain a plurality of recommended work parameters, and sends the plurality of recommended work parameters to the cloud. According to the operation data of the user, the historical user data is searched for and clustered and collaborative filtered to find the historical user data with the highest similarity to the current user, and the recommended result is constructed for the current user through the historical user data, thereby improving the recommendation speed and accuracy.

[0080] Please refer to Figure 3 A flowchart of a data recommendation method is provided for the embodiment of the present application. As shown in Figure 3 The detection method of the embodiment of the present application can include the following steps:

[0081] S101, the wireless wearable electroencephalogram device is used to detect and preprocess the electroencephalogram signal to generate electroencephalogram data and send the electroencephalogram data to the mobile terminal;

[0082] In the embodiment of the present application, after the wireless wearable electroencephalogram device is started and runs, the wireless wearable electroencephalogram device is used to detect and preprocess the electroencephalogram signal to generate electroencephalogram data and send the electroencephalogram data to the mobile terminal.

[0083] In one possible implementation, the user first wears the wireless wearable electroencephalogram device 101 and turns on the device switch, the sensing module 201 in the wireless wearable electroencephalogram device 101 starts to detect the electroencephalogram signal of the user, and calculates the electroencephalogram data according to the electroencephalogram signal, the electroencephalogram data including alpha wave energy, beta wave energy, gamma wave energy, delta wave energy, and theta wave energy. Then the user turns on the mobile terminal 102, respectively configures the wireless sending module 304 and the wireless receiving module 306 connected with the wireless wearable electroencephalogram device 101, and after the connection is successful, the electroencephalogram data is synchronously uploaded to the mobile terminal 102.

[0084] S102, the mobile terminal is used to determine user operation data, and send the received electroencephalogram data and the user operation data to the cloud data processing center;

[0085] In the embodiments of the present application, when the user operation data is determined and the received electroencephalogram data and user operation data are sent to the cloud data processing center, first, when the user registration instruction is received, the personal basic information of the current user is obtained, and then the user input multiple working parameters are received. When the recommended strategy selected by the current user is the default recommended strategy or the self-selected recommended strategy, the personal basic information and the multiple working parameters are displayed. Secondly, the parameter selection instruction for the displayed data is received, and the multiple target values are selected from the basic information and the multiple working parameters based on the parameter selection instruction. The recommended algorithm parameters are generated. Finally, the personal basic information, the multiple working parameters, the recommended algorithm parameters and the received electroencephalogram data are sent to the cloud data processing center.

[0086] In a possible implementation, when the user is a new registered user, all personal information is input on the mobile terminal 102, for example, including the registered user name name, gender, age, date of birth, and previous medical history); The user inputs all working parameters param, including working mode (deep sleep / light rest / learning / leisure / exercise), duration, fixed-point playback, audio selection (audio includes but is not limited to music, hypnosis recording, speech, etc. Any legal downloaded or self-recorded audio); After all personal information and all working parameters are input, the user selects the recommended strategy, and when the user selects the default recommended strategy or the self-selected recommended strategy, all personal information and all working parameters are displayed. The user selects any several parameters in the displayed all personal information and all working parameters as the recommended algorithm parameters. The recommended strategy includes selecting the last configuration / default best recommendation / self-selected recommendation; In the case of default best recommendation and self-selected recommendation, the user selects the label data, including the selected label data in all personal information and the selected label data in all working parameters. After the selection is completed, it is automatically uploaded to the cloud data processing center 103.

[0087] S103, the cloud data processing center is used for retrieving historical user data according to the received user operation data, and sending the to-be-processed user data to the intelligent recommendation server;

[0088] In the embodiment of the present application, when the historical user data is retrieved according to the received user operation data, and the to-be-processed user data is sent to the intelligent recommendation server, first, the received electroencephalogram data is saved, and the received personal basic information, multiple work parameters and recommendation algorithm parameters are saved, then the historical user personal information, historical user work parameters and historical user electroencephalogram data are obtained by searching in the database according to the selected label data in the recommendation algorithm parameters, secondly, the real-time electroencephalogram data, historical user personal information, historical user work parameters and historical user electroencephalogram data are combined to form the to-be-processed user data, and finally the to-be-processed user data is sent to the intelligent recommendation server.

[0089] In a possible implementation, the cloud data processing center 103 saves the received current user electroencephalogram data in real time, saves the personal information of the newly registered user, receives the work parameters of the current user and the recommendation algorithm parameters. If the recommendation strategy is selected as the last time parameter selection configuration, the recommendation result is directly issued to the mobile terminal according to the last time recommendation strategy, otherwise the historical user personal information, historical user work parameters and historical user electroencephalogram data in the database are searched according to the selected label data in the recommendation algorithm parameters, and the searched data and the electroencephalogram data of the current user are combined into historical user data and input to the intelligent recommendation server 104.

[0090] S104, the intelligent recommendation server is used for clustering and collaborative filtering according to the received historical user data and electroencephalogram data, generating filtering data, and performing intersection operation based on the filtering data to generate multiple recommended work parameters and send to the cloud data processing center.

[0091] In the embodiment of the present application, when clustering and collaborative filtering are performed according to the received historical user data and electroencephalogram data to generate filtering data, first, the K-means clustering algorithm is used to cluster the electroencephalogram data in the to-be-processed user data into three groups according to the energy level, to generate multiple clustering results, then the target clustering result to which the five kinds of electroencephalogram energy in the real-time electroencephalogram data belong is determined in the multiple clustering results, to obtain five clustering results, secondly, the user with the most registered user name in the five clustering results is taken as the registered user space, and finally the multiple groups of first user data with the highest similarity are determined in the historical user data according to the recommendation algorithm parameters and the preset collaborative filtering algorithm; the multiple groups of first user data are determined as filtering data.

[0092] Specifically, when the intersection operation is performed based on the filtering data to generate multiple recommended work parameters, first, multiple groups of second user data are searched in the registered user space according to the registered user name, then the intersection operation is performed between the multiple groups of first user data and the multiple groups of second user data to generate intersection user data, and finally the intersection user data is determined as the multiple recommended work parameters.

[0093] In a possible implementation, the intelligent recommendation server 104 clusters the received historical user data into three groups according to energy levels, i.e., high, medium and low, in combination with a K-means clustering algorithm, obtains a plurality of clustering results, calculates which category of the plurality of clustering results the five kinds of brain wave energies in the current user's electroencephalogram data belong to, obtains the clustering results corresponding to the five kinds of brain waves, takes the user whose registered user name appears most frequently in the clustering results corresponding to the five kinds of brain waves as the registered user space K{n}. Meanwhile, according to the label data selected by the current user, the most similar user and the recommended working parameters are found by a collaborative filtering method, denoted as S(name, param)

[100] , and at most 100 groups are saved. Finally, S(name, param)

[10] is found according to the registered user name in K{n}, at most 10 groups are saved, an intersection operation is performed on the 100 groups and the 10 groups, a target solution is obtained, the recommended working parameters param in the solution are output to the cloud data processing center 103.

[0094] Further, the cloud data processing center 103 issues the recommended working parameters param to the mobile terminal 102, the mobile terminal 102 displays the recommended results, the user selects a recommended result for comparison with the original defined working parameters, and finally determines the working parameters, and the feedback part 202 of the wireless wearable electroencephalogram device 101 plays audio according to the configured working parameters. Until the working duration ends or the user actively closes.

[0095] For example Figure 4 as shown, Figure 4 is a process schematic block diagram of a data recommendation process provided by the present application. First, the user wears the wireless wearable electroencephalogram device 101 and turns it on, then connects the wireless wearable electroencephalogram device 101 using the mobile terminal 102, inputs personal information using the mobile terminal 102, selects working parameters, and optionally configures recommendation algorithm parameters. Secondly, the cloud data processing center 103 queries data according to the personal information, working parameters and optional recommendation parameters, and calculates the intersection of the recommended results by using a clustering algorithm and a collaborative filtering algorithm through the intelligent recommendation server 104. Finally, the recommended results are displayed through the mobile terminal 102, the user selects and confirms, the feedback part 202 of the wireless wearable electroencephalogram device 101 plays audio, the sensing part 201 synchronously detects and uploads electroencephalogram data, the mobile terminal 102 displays and uploads electroencephalogram data, and the cloud data processing center 103 stores the electroencephalogram data.

[0096] For example Figure 5 as shown, Figure 5is a flow schematic block diagram of clustering and collaborative filtering, first, the historical user data is clustered by using the K-means clustering method according to the energy levels of the five kinds of brain waves in the electroencephalogram data, and the user five kinds of brain waves are calculated in which cluster, the registered user name of the cluster is extracted, the registered user with the highest number of occurrences is found as the registered user space K{n}, then S(name.param)

[10] is found in K{n}, and the registered user name with the highest user tag similarity and the corresponding working parameter S(name.param)

[100] are found, finally, collaborative filtering is performed according to the user selected tag data (may be gender, age, medical history, working mode, duration, audio selection) to obtain similar personal information and working parameters of the current user.

[0097] It should be noted that the present application does not require professional personnel and skills, and is widely applicable. After a large number of users use and accumulate enough cases, the system effect is continuously optimized, and certain data experience support is also provided for medical rehabilitation.

[0098] In the embodiment of the present application, first, the wireless wearable electroencephalogram device detects and preprocesses the electroencephalogram signal, generates electroencephalogram data and sends it to the mobile terminal, then the mobile terminal determines the user operation data and sends it to the cloud data processing center together with the received electroencephalogram data, secondly, the cloud data processing center retrieves historical user data according to the received user operation data, and sends it to the intelligent recommendation server together with the received electroencephalogram data, finally, the intelligent recommendation server clusters and collaboratively filters the received historical user data and electroencephalogram data, performs intersection operation after filtering data, obtains multiple recommended working parameters and sends them to the cloud. According to the operation data of the user, the historical user data is clustered and collaboratively filtered to find the historical user data with the highest similarity to the current user, and the recommended results are constructed for the current user through the historical user data, thereby improving the recommendation speed and accuracy.

[0099] The present application also provides a computer readable medium having program instructions stored thereon, which, when executed by a processor, implement the data recommendation method provided by each of the above method embodiments.

[0100] The present application also provides a computer program product containing instructions, which, when running on a computer, causes the computer to execute the data recommendation method of each of the above method embodiments.

[0101] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The program can be stored in a computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiment methods can be included. The storage medium can be a magnetic disc, an optical disc, a read-only memory, a random access memory, etc.

[0102] The above only describes the preferred embodiments of the present application, and cannot limit the scope of the present application. Any equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

1. A data recommendation system, characterized by, The system comprises: A wireless wearable electroencephalogram device, a mobile terminal, a cloud data processing center and an intelligent recommendation server; The wireless wearable electroencephalogram device, the mobile terminal, the cloud data processing center and the intelligent recommendation server are in communication connection; The wireless wearable electroencephalogram device is configured to detect and preprocess electroencephalogram signals, generate electroencephalogram data and send the electroencephalogram data to the mobile terminal; The mobile terminal is configured to determine user operation data and send the received electroencephalogram data and the user operation data to the cloud data processing center; wherein The determination of the user operation data and the sending of the received electroencephalogram data and the user operation data to the cloud data processing center comprises: Upon receiving a user registration instruction, obtaining personal basic information of a current user; receiving a plurality of work parameters input by the user; when a recommendation strategy selected by the current user is a default recommendation strategy or a self-selected recommendation strategy, displaying the personal basic information and the plurality of work parameters; receiving a parameter selection instruction for the displayed data, selecting a plurality of target values from the basic information and the plurality of work parameters based on the parameter selection instruction, generating recommendation algorithm parameters; and sending the personal basic information, the plurality of work parameters, the recommendation algorithm parameters and the received electroencephalogram data to the cloud data processing center; The cloud data processing center is configured to retrieve historical user data according to the received user operation data and send the historical user data and the received electroencephalogram data to the intelligent recommendation server; The intelligent recommendation server is configured to perform clustering and collaborative filtering according to the received historical user data and electroencephalogram data, generate filtered data, perform an intersection operation based on the filtered data, generate a plurality of recommended work parameters and send the recommended work parameters to the cloud data processing center; The cloud data processing center is further configured to construct a plurality of recommendation results according to the received recommended work parameters and send the recommendation results to the mobile terminal; The mobile terminal is further configured to display the received plurality of recommendation results and, upon receiving a selection instruction for the plurality of recommendation results, determine a target recommendation result from the plurality of recommendation results and send the target recommendation result to the wireless wearable electroencephalogram device; The wireless wearable electroencephalogram device is further configured to play audio according to the received target recommendation result.

2. The data recommendation system of claim 1, wherein The wireless wearable electroencephalogram device comprises a sensing component and a feedback component; wherein The sensing component and the feedback component are in communication connection; wherein The sensing component is configured to detect and preprocess electroencephalogram signals, generate electroencephalogram data and send the electroencephalogram data to the mobile terminal when a communication connection is established with the mobile terminal; The feedback component is configured to receive a target recommendation result sent from the mobile terminal and play audio based on the target recommendation result.

3. The data recommendation system of claim 2, wherein The sensing component comprises an electroencephalogram electrode, a signal acquisition module, a calculation processing module and a wireless sending module; wherein The electroencephalogram electrode, the signal acquisition module, the calculation processing module and the wireless sending module are electrically connected in sequence. The electroencephalogram electrode and the signal acquisition module are configured to detect and acquire electroencephalogram signals. The calculation processing module is configured to decode and encode the electroencephalogram signals to generate electroencephalogram data, and the wireless sending module is configured to send the electroencephalogram data to the mobile terminal.

4. The data recommendation system of claim 2, wherein the feedback component comprises an audio playing module and a wireless receiving module; wherein the audio playing module and the wireless receiving module are electrically connected; wherein the wireless receiving module is configured to receive a target recommendation result sent from the mobile terminal; and the audio playing module is configured to play audio based on the target recommendation result.

4. The data recommendation system of claim 2, wherein the feedback component comprises an audio playing module and a wireless receiving module; wherein the audio playing module and the wireless receiving module are electrically connected; wherein the wireless receiving module is configured to receive a target recommendation result sent from the mobile terminal; and the audio playing module is configured to play audio based on the target recommendation result. The method comprises: The wireless wearable electroencephalogram device is configured to detect and preprocess electroencephalogram signals to generate electroencephalogram data and send the electroencephalogram data to the mobile terminal; The mobile terminal is configured to determine user operation data and send the received electroencephalogram data and the user operation data to the cloud data processing center; 5. The data recommendation system of claim 1, wherein, The cloud data processing center is configured to retrieve historical user data according to the received user operation data and send the historical user data and the received electroencephalogram data to the intelligent recommendation service end; and The cloud data processing center is configured to retrieve historical user data according to the received user operation data and send the historical user data and the received electroencephalogram data to the intelligent recommendation service end. ​ ​ ​ 6. The data recommendation system of claim 5, wherein, ​ ​ ​ ​ ​ 7. The data recommendation system of claim 6, wherein, ​ ​ ​ ​ 8. A data recommendation method implemented using the system of any one of claims 1-7, characterized by, ​ ​ ​ ​ The intelligent recommendation server is configured to perform clustering and collaborative filtering based on the received historical user data and electroencephalogram data, generate filtered data, perform an intersection operation based on the filtered data, generate a plurality of recommended working parameters, and send the recommended working parameters to the cloud data processing center.

Images