Information Prediction Method, Device, Equipment, Medium

Abstract

The present disclosure provides an information prediction method, apparatus, device, and medium, which can be applied to the fields of artificial intelligence technology and financial technology. The information prediction method includes: collecting the time-series signal of brain waves, where the time-series signal of brain waves is generated when the target object watches the video image of the target product; the time-series signal of brain waves includes band signals of different frequencies; according to the frequency information of the band signals, extracting the time-series signal of the target band from the time-series signal of brain waves, and the time-series signal of the target band includes the power information of the target band and the duration information of the occurrence of the target band; generating the concentration degree of the target object on the target product according to the power information and the duration information, where the concentration degree represents the degree of attention concentration of the target object when watching the video image of the target product; and generating the preference prediction information of the target object on the target product according to the concentration degree.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology and financial technology, and particularly to an information prediction method, apparatus, device, medium, and program product. Background Art

[0002] In traditional business recommendation scenarios, generally, user preferences are analyzed based on data such as user historical purchase records or historical purchase behaviors, and then products that the user may purchase or be interested in are recommended to the user according to the analysis results.

[0003] However, in the process of implementing the concept of the present disclosure, the inventors found that this method has the following defects: data analysis requires a large amount of historical data, and its adaptability to scenarios lacking historical data is poor, resulting in inability to predict or low prediction accuracy. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides an information prediction method, apparatus, device, medium, and program product.

[0005] According to a first aspect of the present disclosure, there is provided an information prediction method, including:

[0006] Collecting a time series signal of brain waves, where the time series signal of brain waves is generated when a target object watches a video image of a target product; the time series signal of brain waves includes band signals of different frequencies;

[0007] Extracting a time series signal of a target band from the time series signal of brain waves according to the frequency information of the band signal, where the time series signal of the target band includes power information of the target band and duration information of the occurrence of the target band;

[0008] Generating a concentration degree of the target object on the target product according to the power information and the duration information, where the concentration degree represents the degree of attention concentration of the target object when watching the video image of the target product; and

[0009] Generating preference prediction information of the target object on the target product according to the concentration degree.

[0010] According to an embodiment of the present disclosure, extracting a time series signal of a target band from the time series signal of brain waves according to the frequency information of the band signal includes:

[0011] Converting the time series signal of brain waves into a frequency domain signal of brain waves through Fourier transform;

[0012] Using a power spectral density algorithm to extract a time series signal of a target band from the time series signal of brain waves according to the frequency information of the band signal.

[0013] According to an embodiment of the present disclosure, the target band includes N bands, where N is a positive integer greater than 2. Generating the degree of concentration of the target object on the target product based on the power information and the duration information includes:

[0014] Generating the power information of the Nth band according to the initial power of the Nth band and the first preset weight coefficient of the Nth band;

[0015] Generating the duration information of the Nth band according to the initial duration of the appearance of the Nth band and the second preset weight coefficient of the Nth band;

[0016] Generating the degree of concentration corresponding to the Nth band according to the power information of the Nth band and the duration information of the Nth band;

[0017] Generating the degree of concentration of the target object on the target product according to the degrees of concentration corresponding to the N bands in the target band.

[0018] According to an embodiment of the present disclosure, the target product includes M products. Generating the preference prediction information of the target object for the target product based on the degree of concentration includes:

[0019] Sorting the degrees of concentration corresponding to the M products to obtain a sorting result;

[0020] Generating the preference prediction information of the target object for the M products according to the sorting result.

[0021] According to an embodiment of the present disclosure, the above information prediction method further includes:

[0022] Generating recommendation information according to the preference prediction information;

[0023] Sending the recommendation information to the target object.

[0024] According to an embodiment of the present disclosure, generating recommendation information according to the preference prediction information includes:

[0025] Extracting preference feature information from the preference prediction information;

[0026] Determining the product information to be recommended from the product database according to the preference feature information;

[0027] Generating recommendation information according to the product information to be recommended.

[0028] According to an embodiment of the present disclosure, sending the recommendation information to the target object includes:

[0029] Determining the recommendation frequency according to the preference prediction information;

[0030] Sending the recommendation information to the target object according to the recommendation frequency.

[0031] Another aspect of the present disclosure provides an information prediction device, including: an acquisition module, an extraction module, a first generation module, and a second generation module. Among them, the acquisition module is configured to acquire the time-series signal of the brain wave, where the time-series signal of the brain wave is generated when the target object watches the video image of the target product; the time-series signal of the brain wave includes band signals of different frequencies. The extraction module is configured to extract the time-series signal of the target band from the time-series signal of the brain wave according to the frequency information of the band signal, and the time-series signal of the target band includes the power information of the target band and the duration information of the appearance of the target band. The first generation module is configured to generate the concentration degree of the target object on the target product according to the power information and the duration information, where the concentration degree represents the degree of attention concentration of the target object when watching the video image of the target product. The second generation module is configured to generate the preference prediction information of the target object on the target product according to the concentration degree.

[0032] According to an embodiment of the present disclosure, the extraction module includes a conversion unit and a first extraction unit. Among them, the conversion unit is configured to convert the time-series signal of the brain wave into the frequency-domain signal of the brain wave through Fourier transform. The first extraction unit is configured to use the power spectral density algorithm to extract the time-series signal of the target band from the time-series signal of the brain wave according to the frequency information of the band signal.

[0033] According to an embodiment of the present disclosure, the first generation module includes a first generation unit, a second generation unit, a third generation unit, and a fourth generation unit. Among them, the first generation unit is configured to generate the power information of the Nth band according to the initial power of the Nth band and the first preset weight coefficient of the Nth band. The second generation unit is configured to generate the duration information of the Nth band according to the initial duration of the appearance of the Nth band and the second preset weight coefficient of the Nth band. The third generation unit is configured to generate the concentration degree corresponding to the Nth band according to the power information of the Nth band and the duration information of the Nth band. The fourth generation unit is configured to generate the concentration degree of the target object on the target product according to the concentration degrees corresponding to the N bands in the target band.

[0034] According to an embodiment of the present disclosure, the second generation module includes a sorting unit and a fifth generation unit. Among them, the sorting unit is configured to sort the concentration degrees corresponding to M products to obtain a sorting result. The fifth generation unit is configured to generate the preference prediction information of the target object on the M products according to the sorting result.

[0035] According to an embodiment of the present disclosure, the above information prediction device further includes a third generation module and a sending module. Among them, the third generation module is configured to generate recommendation information according to the preference prediction information. The sending module is configured to send the recommendation information to the target object.

[0036] According to an embodiment of the present disclosure, the third generation module includes a second extraction unit, a first determination unit, and a sixth generation unit. The second extraction unit is configured to extract preference feature information from the preference prediction information. The first determination unit is configured to determine the product information to be recommended from the product database according to the preference feature information. The sixth generation unit is configured to generate recommendation information according to the product information to be recommended.

[0037] According to an embodiment of the present disclosure, the sending module includes a second determination unit and a sending unit. Among them, the second determination unit is configured to determine the recommendation frequency according to the preference prediction information. The sending unit is configured to send the recommendation information to the target object according to the recommendation frequency.

[0038] Another aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the above information prediction method.

[0039] Another aspect of the present disclosure further provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the above information prediction method.

[0040] Another aspect of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above information prediction method is implemented.

[0041] According to an embodiment of the present disclosure, by collecting the time series signal of the brain wave generated when the target object watches the video image of the target product, extracting the time series signal of the target band from the time series signal of the brain wave, generating the concentration degree of the target object on the target product according to the power information of the target band and the duration information of the appearance of the target band, and generating the preference prediction information of the target object on the target product according to the concentration degree. Since the concentration degree of the target object on the target product is obtained by collecting the time series signal of the brain wave, and the time series signal of the brain wave is generated when the target object watches the video image of the target product, it at least partially solves the problem of poor applicability caused by relying on a large amount of historical data in the related art. Moreover, the preference prediction information of the target object on the target product is generated according to the degree of attention when the target object watches the video image of the target product, which improves the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above content and other objects, features and advantages of the present disclosure will become clearer. In the drawings:

[0043] Figure 1Schematically shows an application scenario diagram of an information prediction method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0044] Figure 2 Schematically shows a flowchart of an information prediction method according to an embodiment of the present disclosure;

[0045] Figure 3 Schematically shows a flowchart of a method for extracting time series signals of a target band according to an embodiment of the present disclosure;

[0046] Figure 4 Schematically shows a flowchart of a method for generating the degree of concentration of a target object on a target product according to an embodiment of the present disclosure;

[0047] Figure 5 Schematically shows a display diagram of preference prediction information of a target object according to an embodiment of the present disclosure;

[0048] Figure 6 Schematically shows a structural block diagram of an information prediction apparatus according to an embodiment of the present disclosure; and

[0049] Figure 7 Schematically shows a block diagram of an electronic device suitable for implementing the information prediction method according to an embodiment of the present disclosure. Detailed implementation manners

[0050] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0051] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0052] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0053] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning that those skilled in the art usually understand this expression (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0054] It should be noted that the information prediction method and device of the present disclosure can be used in the financial field and the artificial intelligence technology field, and can also be used in any field other than the financial field. The application field of the information prediction method and device of the present disclosure is not limited.

[0055] In the technical solution of the present disclosure, the processing of the collection, storage, use, processing, transmission, provision, disclosure, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good customs.

[0056] In the technical solution of the present disclosure, before obtaining or collecting the user's personal information, the authorization or consent of the user is obtained.

[0057] The embodiment of the present disclosure provides an information prediction method. By collecting the time series signal of the brain wave generated when the target object watches the video image of the target product, extracting the time series signal of the target band from the time series signal of the brain wave, generating the concentration degree of the target object on the target product according to the power information of the target band and the duration information of the appearance of the target band, and generating the preference prediction information of the target object on the target product according to the concentration degree. Since the concentration degree of the target object on the target product is obtained by collecting the time series signal of the brain wave, and the time series signal of the brain wave is generated when the target object watches the video image of the target product, it at least partially solves the problem of poor applicability caused by relying on a large amount of historical data in the related technology. Moreover, the preference prediction information of the target object on the target product is generated according to the degree of attention of the target object when watching the video image of the target product, which improves the accuracy of the prediction.

[0058] Figure 1 Schematically shows an application scenario diagram of the information prediction method according to an embodiment of the present disclosure.

[0059] As Figure 1 shown, the application scenario 100 according to this embodiment may include a display device 101, an electroencephalogram device 102, a user 103, a network 104, and a server 105. The network 104 is used to provide a medium for the communication link between the electroencephalogram device 102 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0060] User 103 can view the video image of the target product through the display device 101, and the electroencephalogram device 102 can use a multi-channel electrode cap to record the electroencephalogram signal data of user 103 when viewing the video image of the target product.

[0061] The electroencephalogram device 102 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop computers, desktop computers, and so on.

[0062] The server 105 can be a server that provides various services, such as analyzing and processing the electroencephalogram signal data of user 103 collected by the electroencephalogram device 102, and feeding back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the electroencephalogram device 102.

[0063] It should be noted that the information prediction method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the information prediction device provided by the embodiments of the present disclosure can generally be set in the server 105. The information prediction method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the electroencephalogram device 102 and / or the server 105. Correspondingly, the information prediction device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the electroencephalogram device 102 and / or the server 105.

[0064] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0065] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 1 Based on the scenario described below Figures 2 to 5 the information prediction method of the public embodiments will be described in detail through

[0066] Figure 2 Schematically shows a flowchart of the information prediction method according to an embodiment of the present disclosure.

[0067] As Figure 2 shown, the information prediction method of this embodiment includes operations S210 to S240.

[0068] In operation S210, the timing signal of the electroencephalogram is collected, where the timing signal of the electroencephalogram is generated when the target object views the video image of the target product; the timing signal of the electroencephalogram includes band signals of different frequencies.

[0069] According to an embodiment of the present disclosure, the time-series signal of brain waves, also known as electroencephalogram (EEG) signals, is the overall reflection of the spontaneous and rhythmic electrical activities of brain cell groups on the cerebral cortex and scalp, and can be monitored by electrodes placed on the scalp. The time-series signal of the brain waves of the target object can be collected in real time by connecting a brain-computer interface device to the target object when the target object views the video image of the target product. In order to make the collected brain wave signals tend to be stable, before playing the video image of the target product, a video image that can improve the concentration of the target object's attention can be played first, such as the ascent and descent of an airplane, the left and right movement of a person, etc., so that the target object enters a preparatory state in advance and the brain wave signals of the target object tend to be stable.

[0070] According to an embodiment of the present disclosure, the video image of the target product can be played to the target object at regular intervals. For example, the target product may include M products, and the time interval between the video images of the (M - 1)-th product and the M-th product is T seconds, so as to collect the time-series signals of the brain waves of the target object for the M products.

[0071] In operation S220, according to the frequency information of the band signal, the time-series signal of the target band is extracted from the time-series signal of the brain waves, and the time-series signal of the target band includes the power information of the target band and the duration information of the appearance of the target band.

[0072] According to an embodiment of the present disclosure, the time-series signal of brain waves is usually decomposed into 5 bands according to different frequencies: delta band (0 - 3.5 hz), theta band (4 - 7 hz), alpha band (8 - 12 hz), beta band (13 - 30 hz), gamma band (> 30 hz). In the human body's brain waves, when a person is excited and nervous, the brain will generate beta waves; when the body is relaxed and the eyes are closed, alpha waves will be generated and disappear instantly when the eyes are opened, that is, it is the main activity frequency mainly in a quiet and waking state; when a person is sleepy, the EEG will trigger theta waves; when a person enters a deep sleep state, the EEG activity frequency drops to the lowest, and delta waves appear. The EEG signals of the four frequencies correspond to the time-domain waveforms of the four frequencies; at the same time, when a person's attention is not concentrated and the interest in things is low, the theta EEG activity and the theta / beta power ratio increase, and the activities of beta and alpha decrease; on the contrary, when the theta EEG activity and the theta / beta power ratio decrease and the activities of beta and alpha increase, the person is more focused.

[0073] According to an embodiment of the present disclosure, the target frequency bands may include the delta band, the theta band, the alpha band, and the beta band. Before extracting the time series signals of the target frequency bands, the time series signals of the collected electroencephalogram may be preprocessed first. For example, a band-pass filter with a frequency range of 0.1 to 49.5 Hz may be used to filter the time series signals of the electroencephalogram to remove high-frequency noise signals, such as electrooculogram signals, electromyogram signals, and so on.

[0074] According to an embodiment of the present disclosure, since the time series signals of the collected electroencephalogram are in the time domain, the time domain signals may be converted into frequency domain signals, and then, according to the frequency information of different frequency bands, the time series signals of the target frequency bands such as the delta band, the theta band, the alpha band, and the beta band may be extracted from the time series signals of the electroencephalogram.

[0075] According to an embodiment of the present disclosure, since the cerebral cortex often spontaneously generates rhythmic potential changes without obvious stimuli, a support vector machine (SVM) may be used to classify different frequency bands in the time series signals of the electroencephalogram, so as to obtain the time series signals of the target frequency bands.

[0076] In operation S230, according to the power information and the duration information, the degree of concentration of the target object on the target product is generated, where the degree of concentration represents the degree of attention concentration of the target object when viewing the video image of the target product.

[0077] According to an embodiment of the present disclosure, when a person's attention is not concentrated and the interest in things is relatively low, the theta electroencephalogram activity and the theta wave / beta wave power ratio increase, and the activities of beta and alpha decrease; on the contrary, when the theta electroencephalogram activity and the theta wave / beta wave power ratio decrease, and the activities of the beta wave and the alpha wave increase, the person is more concentrated. The degree of concentration of the target object on the target product may be calculated according to the power of each wave and the duration information of the appearance of this wave. For example: the duration of the target object viewing the video image of the target product A is Ts, that is, from time t1 to time t2. During this time period, the power of the beta wave and the alpha wave is relatively high, then it may be determined that the degree of concentration of the target object on the target product A is relatively high.

[0078] In operation S240, according to the degree of concentration, the preference prediction information of the target object for the target product is generated.

[0079] According to an embodiment of the present disclosure, for example: the degree of concentration of the target object on the target product A is m, and the degree of concentration on the target product B is n, where m is greater than n, which means that the target object is more interested in the target product A than in the target product B. The preference prediction information of the target object for the target product A may be generated.

[0080] By collecting the time-series signal of the brain waves generated when the target object watches the video image of the target product, extracting the time-series signal of the target band from the time-series signal of the brain waves, generating the concentration of the target object on the target product according to the power information of the target band and the duration information of the appearance of the target band, and generating the preference prediction information of the target object on the target product according to the concentration. Since the concentration of the target object on the target product is obtained by collecting the time-series signal of the brain waves, and the time-series signal of the brain waves is generated when the target object watches the video image of the target product, it at least partially solves the problem of poor applicability caused by relying on a large amount of historical data in the related technology. Moreover, the preference prediction information of the target object on the target product is generated according to the degree of attention when the target object watches the video image of the target product, which improves the accuracy of the prediction.

[0081] Figure 3 Schematically shows a flowchart of a method for extracting the time-series signal of a target band according to an embodiment of the present disclosure.

[0082] As Figure 3 shown, the method for extracting the time-series signal of the target band in this embodiment includes operations S310 to S320.

[0083] In operation S310, the time-series signal of the brain waves is transformed into the frequency-domain signal of the brain waves through Fourier transform.

[0084] In operation S320, using the power spectral density algorithm, according to the frequency information of the band signal, the time-series signal of the target band is extracted from the time-series signal of the brain waves.

[0085] According to an embodiment of the present disclosure, the power spectral density in the frequency-domain signal of the brain waves can be extracted by using the welch method in Matlab software, and then the power spectrum can be calculated by using the pwelch function, and the power information of the target band can be extracted by using the bandpower function to obtain the power information of the target band. For example: when the target object watches the target product A (during t 01 ~t 02 ), the power of the delta band can be p1, the power of the theta band can be p2, the power of the alpha band can be p3, and the power of the beta band can be p4. The time interval when the delta band appears can be t1~t2, and the time interval when the theta band appears can be t1~t3, where t1, t2, and t3 are all within the time interval t 01 ~t 02 ).

[0086] According to an embodiment of the present disclosure, by converting the time-domain signal of the brain wave into a frequency-domain signal and using the power spectral density algorithm to extract the time-series signal of the target band from the time-domain signal of the brain wave, the degree of concentration of the target object on the target product can be determined by analyzing the change of the signal of the target band in the brain wave signal in real time, thereby improving the accuracy of predicting the preference information of the target object for the target product.

[0087] Figure 4 Schematically shows a flowchart of a method for generating the degree of concentration of a target object on a target product according to an embodiment of the present disclosure.

[0088] As Figure 4 shown, the method for generating the degree of concentration of the target object on the target product in this embodiment includes operations S410 to S440.

[0089] In operation S410, power information of the Nth band is generated according to the initial power of the Nth band and the first preset weight coefficient of the Nth band.

[0090] In operation S420, duration information of the Nth band is generated according to the initial duration of the appearance of the Nth band and the second preset weight coefficient of the Nth band.

[0091] In operation S430, the degree of concentration corresponding to the Nth band is generated according to the power information of the Nth band and the duration information of the Nth band.

[0092] In operation S440, the degree of concentration of the target object on the target product is generated according to the degrees of concentration corresponding to the N bands in the target band.

[0093] According to an embodiment of the present disclosure, the power of the N bands can be set to A n , where n = 1, 2, 3, 4. A1 can represent the power of the delta band, A2 can represent the power of the theta band, A3 can represent the power of the alpha band, and A4 can represent the power of the beta band. The duration information corresponding to the appearance of the N bands can be expressed as Ti, where i = 1, 2, 3, 4. T1 can represent the duration of the appearance of the delta band, T2 can represent the duration of the appearance of the theta band, T3 can represent the duration of the appearance of the alpha band, and T4 can represent the duration of the appearance of the beta band.

[0094] According to an embodiment of the present disclosure, the first preset weight coefficient can be the weight coefficient corresponding to the band type, and the second preset weight coefficient can be the weight coefficient corresponding to the duration of the appearance of different band types. For example, when a person's attention is concentrated, the activities of the beta wave and the alpha wave are enhanced, and the first preset weight coefficient and the second preset weight coefficient corresponding to the beta wave and the alpha wave can be set higher.

[0095] According to an embodiment of the present disclosure, the concentration can be calculated according to the formula shown in Equation (1):

[0096]

[0097] Where K represents the concentration, A n represents the power of the target band, V n represents the weight coefficient corresponding to the band type, T i represents the duration of the appearance of the target band, W i represents the weight coefficient corresponding to the duration of the appearance of different band types.

[0098] According to an embodiment of the present disclosure, in Equation (1), the weight coefficient V corresponding to the band type satisfies V1 < V2 < V3 < V4. The weight coefficient W corresponding to the duration of the appearance of different band types satisfies W1 < W2 < W3 < W4.

[0099] According to an embodiment of the present disclosure, it can be seen from Equation (1) that when the power and the appearance duration of the beta wave and the alpha wave are longer, the higher the value of the concentration K.

[0100] According to an embodiment of the present disclosure, by analyzing the power and the appearance duration of the target band in the electroencephalogram signal of the target object when watching the video image of the target product, the concentration of the target object on the target product is determined, which can truly reflect the attention degree of the target object when watching the video image of the target product, and can accurately predict the preference information of the target object.

[0101] According to an embodiment of the present disclosure, the target product includes M products. According to the concentration, preference prediction information of the target object for the target product is generated, including:

[0102] Sort the concentrations corresponding to the M products to obtain a sorting result;

[0103] According to the sorting result, preference prediction information of the target object for the M products is generated.

[0104] According to an embodiment of the present disclosure, the concentrations of the M products are K1, K2...K m , where K1 < K2 <...K m It is possible to directly sort according to the numerical values of the concentrations, or to screen some products from the M products for sorting of the concentrations by setting a preset threshold. For example: the preset threshold is K0, K2 < K0 < K3, and only K3...K m can be sorted to obtain a sorting result.

[0105] According to an embodiment of the present disclosure, a higher degree of concentration indicates that the target object is more interested in the target product. For example: the degree of concentration of the target object on the target product A is K1, and the degree of concentration of the target object on the target product B is K2, and K1 < K2, then the generated preference prediction information may be that the preferred product of the target object is the target product B.

[0106] According to an embodiment of the present disclosure, generating preference prediction information of the target object for the product based on the sorting result of the degree of concentration improves the accuracy of preference information prediction.

[0107] According to an embodiment of the present disclosure, the above information prediction method further includes:

[0108] Generating recommendation information according to the preference prediction information;

[0109] Sending the recommendation information to the target object.

[0110] According to an embodiment of the present disclosure, the recommendation information may be the same product information as the preference prediction information or the same type of product information. For example: the preference prediction information is that the preferred product of the target object is the target product B, and the generated recommendation information may be the target product B, or a product of the same type as the target product B.

[0111] According to an embodiment of the present disclosure, sending the recommendation information to the target object may include the product information to be recommended and the suggestion information related to the product to be recommended. For example: the product to be recommended may be an investment product, and the suggestion information related to the product to be recommended may be the investment suggestion information of the investment product, etc.

[0112] According to an embodiment of the present disclosure, since the recommendation information is generated according to the preference prediction information, and the preference prediction information is obtained according to the real brain electrical signals of the target object, the accuracy is relatively high. Therefore, the efficiency of information recommendation is improved.

[0113] According to an embodiment of the present disclosure, generating recommendation information according to the preference prediction information includes:

[0114] Extracting preference feature information from the preference prediction information;

[0115] Determining the product information to be recommended from the product database according to the preference feature information;

[0116] Generating recommendation information according to the product information to be recommended.

[0117] According to an embodiment of the present disclosure, the preference feature information may include product features in the preference prediction information. For example, the preference prediction information includes investment product A, investment product B, and investment product C. Among them, the investment risk levels of investment product A, investment product B, and investment product C are all medium risk levels. The preference feature information that can be extracted from the preference prediction information is investment products with medium risk levels.

[0118] According to an embodiment of the present disclosure, investment products with medium risk levels can be queried from the product database, and the queried investment products with medium risk levels are used as products to be recommended to generate recommendation information. For example, the investment products with medium risk levels queried from the database may include investment products A to E, and the generated recommendation information may be "The products recommended for you are investment products A to E".

[0119] According to an embodiment of the present disclosure, by extracting preference feature information from the preference prediction information and then determining the information of products to be recommended from the product database according to the preference feature information, the scope of the recommendation information can be expanded targeted, and the information recommendation efficiency can be improved.

[0120] According to an embodiment of the present disclosure, sending recommendation information to the target object includes:

[0121] Determining the recommendation frequency according to the preference prediction information;

[0122] Sending the recommendation information to the target object according to the recommendation frequency.

[0123] According to an embodiment of the present disclosure, the recommendation frequency can be determined according to the preference prediction information. For products with a higher degree of preference, the recommendation frequency can be appropriately increased. For example: the focus of target product A is K1, and the focus of target product B is K2, where K1 < K2. The recommendation frequency of target product A can be once a day, and the recommendation frequency of target product B can be twice a day.

[0124] According to an embodiment of the present disclosure, since the frequency of sending recommendation information to the target object is determined according to the preference prediction information, the information recommendation efficiency can be improved.

[0125] Figure 5 A display diagram of the preference prediction information of the target object according to an embodiment of the present disclosure is schematically shown.

[0126] As Figure 5As shown, the upper part of the display figure shows the degree of concentration of the target object on different products. The degree of concentration of the target object on target product A is 13, on target product B is 8, on target product C is 2, on target product D is 5, on target product E is 1, and on target product F is 6. The lower part of the display figure can show the preference prediction information "Your preference is XX type of product" and the recommendation information "We recommend YY product"

[0127] Based on the above information prediction method, the present disclosure also provides an information prediction device. The following will be combined with Figure 6 to describe this device in detail

[0128] Figure 6 Schematically shows a structural block diagram of an information prediction device according to an embodiment of the present disclosure

[0129] As Figure 6 shown, the information prediction 600 of this embodiment includes an acquisition module 610, an extraction module 620, a first generation module 630, and a second generation module 640

[0130] The acquisition module 610 is used to acquire the time series signal of brain waves, where the time series signal of brain waves is generated when the target object watches the video image of the target product; the time series signal of brain waves includes band signals of different frequencies. In one embodiment, the acquisition module 610 can be used to perform the operation S210 described above, which will not be elaborated here

[0131] The extraction module 620 is used to extract the time series signal of the target band from the time series signal of brain waves according to the frequency information of the band signal. The time series signal of the target band includes the power information of the target band and the duration information of the occurrence of the target band. In one embodiment, the extraction module 620 can be used to perform the operation S220 described above, which will not be elaborated here

[0132] The first generation module 630 is used to generate the degree of concentration of the target object on the target product according to the power information and the duration information, where the degree of concentration characterizes the degree of attention concentration of the target object when watching the video image of the target product. In one embodiment, the first generation module 630 can be used to perform the operation S230 described above, which will not be elaborated here

[0133] The second generation module 640 is used to generate the preference prediction information of the target object on the target product according to the degree of concentration. In one embodiment, the second generation module 640 can be used to perform the operation S240 described above, which will not be elaborated here

[0134] According to an embodiment of the present disclosure, the extraction module includes a conversion unit and a first extraction unit. Among them, the conversion unit is used to convert the time-series signal of the brain wave into a frequency-domain signal of the brain wave through Fourier transform. The first extraction unit is used to extract the time-series signal of the target band from the time-series signal of the brain wave by using the power spectral density algorithm according to the frequency information of the band signal.

[0135] According to an embodiment of the present disclosure, the first generation module includes a first generation unit, a second generation unit, a third generation unit, and a fourth generation unit. Among them, the first generation unit is used to generate the power information of the Nth band according to the initial power of the Nth band and the first preset weight coefficient of the Nth band. The second generation unit is used to generate the duration information of the Nth band according to the initial duration of the Nth band appearing and the second preset weight coefficient of the Nth band. The third generation unit is used to generate the concentration corresponding to the Nth band according to the power information of the Nth band and the duration information of the Nth band. The fourth generation unit is used to generate the concentration of the target object on the target product according to the concentrations corresponding to the N bands in the target band.

[0136] According to an embodiment of the present disclosure, the second generation module includes a sorting unit and a fifth generation unit. Among them, the sorting unit is used to sort the concentrations corresponding to the M products to obtain a sorting result. The fifth generation unit is used to generate preference prediction information of the target object for the M products according to the sorting result.

[0137] According to an embodiment of the present disclosure, the above information prediction device further includes a third generation module and a sending module. Among them, the third generation module is used to generate recommendation information according to the preference prediction information. The sending module is used to send the recommendation information to the target object.

[0138] According to an embodiment of the present disclosure, the third generation module includes a second extraction unit, a first determination unit, and a sixth generation unit. The second extraction unit is used to extract preference feature information from the preference prediction information. The first determination unit is used to determine the product information to be recommended from the product database according to the preference feature information. The sixth generation unit is used to generate recommendation information according to the product information to be recommended.

[0139] According to an embodiment of the present disclosure, the sending module includes a second determination unit and a sending unit. Among them, the second determination unit is used to determine the recommendation frequency according to the preference prediction information. The sending unit is used to send the recommendation information to the target object at the recommendation frequency.

[0140] According to an embodiment of the present disclosure, any plurality of modules among the acquisition module 610, the extraction module 620, the first generation module 630, and the second generation module 640 may be combined and implemented in one module, or any one of them may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 610, the extraction module 620, the first generation module 630, and the second generation module 640 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable means such as hardware or firmware through circuit integration or packaging, or may be implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, at least one of the acquisition module 610, the extraction module 620, the first generation module 630, and the second generation module 640 may be at least partially implemented as a computer program module, and when the computer program module is run, corresponding functions may be executed.

[0141] Figure 7 A block diagram of an electronic device suitable for implementing the information prediction method according to an embodiment of the present disclosure is schematically shown.

[0142] As Figure 7 shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage section 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 701 may also include on-board memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0143] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 702 and / or the RAM 703. It should be noted that the programs may also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0144] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, and the input / output (I / O) interface 705 is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0145] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0146] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include one or more memories other than the above-described ROM 702 and / or RAM 703 and / or ROM 702 and RAM 703.

[0147] An embodiment of the present disclosure also includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to cause the computer system to implement the above method provided by the embodiment of the present disclosure.

[0148] When the computer program is executed by the processor 701, it executes the above functions defined in the system / apparatus of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0149] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 709, and / or be installed from the removable medium 711. The program code included in the computer program may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0150] In such an embodiment, the computer program may be downloaded and installed from the network through the communication part 709, and / or be installed from the removable medium 711. When the computer program is executed by the processor 701, it executes the above functions defined in the system of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0151] According to embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0153] Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present disclosure can be combined or / and combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0154] The embodiments of the present disclosure have been described above. However, these embodiments are merely for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. An information prediction method, comprising: Collecting the time series signal of brain waves, wherein the time series signal of brain waves is generated when a target object watches a video image of a target product; the time series signal of brain waves includes band signals of different frequencies; Extracting the time series signal of a target band from the time series signal of brain waves according to the frequency information of the band signal, wherein the time series signal of the target band includes the power information of the target band and the duration information of the occurrence of the target band; Generating the concentration degree of the target object on the target product according to the power information and the duration information, wherein the concentration degree characterizes the degree of attention concentration of the target object when watching the video image of the target product; and Generating preference prediction information of the target object for the target product according to the concentration degree; Wherein, the target band includes N bands, N is a positive integer greater than 2, and the generating the concentration degree of the target object on the target product according to the power information and the duration information includes: Generating the power information of the Nth band according to the initial power of the Nth band and the first preset weight coefficient of the Nth band; the first preset weight coefficient is the weight coefficient corresponding to the band type; Generating the duration information of the Nth band according to the initial duration of the occurrence of the Nth band and the second preset weight coefficient of the Nth band; the second preset weight coefficient is the weight coefficient corresponding to the duration of the occurrence of different band types; Generating the concentration degree corresponding to the Nth band according to the power information of the Nth band and the duration information of the Nth band; Generating the concentration degree of the target object on the target product according to the concentration degrees corresponding to the N bands in the target band; As shown in formula (1): （1） Among them, K represents the degree of concentration, A n represents the power of the target band, V n represents the weight coefficient corresponding to the band type, T i represents the duration of the appearance of the target band, W i represents the weight coefficient corresponding to the duration of the appearance of different band types.

2. The method according to claim 1, wherein The extracting the time series signal of the target band from the time series signal of brain waves according to the frequency information of the band signal includes: Converting the time series signal of brain waves into the frequency domain signal of brain waves through Fourier transform; Using the power spectral density algorithm to extract the time series signal of the target band from the time series signal of brain waves according to the frequency information of the band signal.

3. The method according to claim 1, wherein The target product includes M products, and the generating the preference prediction information of the target object for the target product according to the concentration degree includes: Sorting the concentration degrees corresponding to the M products to obtain a sorting result; Generating the preference prediction information of the target object for the M products according to the sorting result.

4. The method according to claim 3, further comprising: Generating recommendation information according to the preference prediction information; Sending the recommendation information to the target object.

5. The method according to claim 4, wherein The generating the recommendation information according to the preference prediction information includes: Extracting preference feature information from the preference prediction information; Determining the product information to be recommended from the product database according to the preference feature information; Generating recommendation information according to the product information to be recommended.

6. The method according to claim 4, wherein, The sending the recommendation information to the target object includes: Determining the recommendation frequency according to the preference prediction information; Send the recommendation information to the target object at the recommended frequency.

7. An information prediction device, comprising: An acquisition module, configured to acquire a time series signal of brain waves, wherein the time series signal of brain waves is generated when a target object views a video image of a target product; the time series signal of brain waves includes band signals of different frequencies; An extraction module, configured to extract a time series signal of a target band from the time series signal of brain waves according to the frequency information of the band signal, wherein the time series signal of the target band includes power information of the target band and duration information of the occurrence of the target band; A first generation module, configured to generate a degree of concentration of the target object on the target product according to the power information and the duration information, wherein the degree of concentration characterizes the degree of concentration of the target object's attention when viewing the video image of the target product; A second generation module, configured to generate preference prediction information of the target object for the target product according to the degree of concentration; Wherein, the target band includes N bands, N is a positive integer greater than 2, and the first generation module is configured to: Generate power information of the Nth band according to the initial power of the Nth band and the first preset weight coefficient of the Nth band; the first preset weight coefficient is a weight coefficient corresponding to the band type; Generate duration information of the Nth band according to the initial duration of the occurrence of the Nth band and the second preset weight coefficient of the Nth band; the second preset weight coefficient is a weight coefficient corresponding to the duration of the occurrence of different band types; Generate a degree of concentration corresponding to the Nth band according to the power information of the Nth band and the duration information of the Nth band; Generate the degree of concentration of the target object on the target product according to the degrees of concentration corresponding to the N bands in the target band; As shown in formula (1): （1） Among them, K represents the concentration, A n represents the power of the target band, V n represents the weight coefficient corresponding to the band type, T i represents the duration of the target band appearance, W i represents the weight coefficient corresponding to the duration of different band type appearances.

8. An electronic device, comprising: One or more processors; A storage device, configured to store one or more programs, Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, having executable instructions stored thereon, which when executed by a processor cause the processor to execute the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, which when executed by a processor implements the method according to any one of claims 1 to 6.

Images