A user review recommendation system for terahertz data

Abstract

The application relates to the technical field of data auditing, and discloses a user auditing and recommending system for terahertz data, which comprises a collecting unit configured to construct all the terahertz data to be audited into a terahertz data chain to be audited according to a comparison result; a processing unit configured to determine an initial recommendation weight of the terahertz data chain to be audited according to a use score; a judging unit configured to judge whether the initial recommendation weight is adjusted according to a comprehensive weight influence value; an adjusting unit configured to adjust the initial recommendation weight according to an adjustment coefficient determined according to the comparison result and obtain a final recommendation weight; and an executing unit configured to push the terahertz data chain to be audited to a user interface based on the final recommendation weight. The application can effectively improve the auditing efficiency and recommendation accuracy of the terahertz data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data auditing, in particular to a user auditing and recommendation system for terahertz data. BACKGROUND

[0002] Terahertz data plays a crucial role in modern scientific and technological fields, especially in information technology, data analysis, and Internet of Things applications. With the rapid development of terahertz technology, it has shown great application potential in imaging, communication, security detection, and other fields. However, in the face of massive terahertz data, how to efficiently filter, audit, and recommend valuable information to users has become a problem that needs to be solved.

[0003] Therefore, it is necessary to design a user auditing and recommendation system for terahertz data to solve the problems existing in the current technology. SUMMARY

[0004] In view of this, the present application provides a user auditing and recommendation system for terahertz data, aiming to solve the problem of inefficient filtering and auditing of massive terahertz data in the current technology.

[0005] On the one hand, the present application provides a user auditing and recommendation system for terahertz data, comprising:

[0006] The acquisition unit is configured to acquire the terahertz data to be audited from different data sources, obtain the spectral feature value and data type information of each terahertz data to be audited, compare the spectral feature value of each terahertz data to be audited with the corresponding feature value threshold, and construct all the terahertz data to be audited into a terahertz data chain to be audited according to the comparison result;

[0007] The processing unit is configured to verify the integrity of the terahertz data chain to be audited; when the processing unit determines that the data of the terahertz data chain to be audited is complete, it determines the use score of the terahertz data chain to be audited, and determines the initial recommendation weight of the terahertz data chain to be audited according to the use score;

[0008] The judgment unit is configured to control the acquisition unit to acquire the weight influence value of all the data sources, calculate the comprehensive weight influence value, and determine whether to adjust the initial recommendation weight according to the comprehensive weight influence value;

[0009] The adjustment unit is configured to adjust the initial recommendation weight when it is determined that the initial recommendation weight is adjusted, compare the initial recommendation weight and the comprehensive weight influence value as a feature vector with a historical recommendation scheme, adjust the initial recommendation weight according to the adjustment coefficient according to the comparison result, and obtain the final recommendation weight;

[0010] an execution unit configured to push the to-be-audited terahertz data chain to a user interface based on the final recommendation weight.

[0011] Further, the spectral feature values include frequency, amplitude, phase, and bandwidth.

[0012] Further, when all the to-be-audited terahertz data are constructed into the to-be-audited terahertz data chain according to the comparison result, the method further includes:

[0013] data whose spectral feature values are greater than corresponding threshold values are classified into a first audit set, the number of to-be-audited terahertz data in the first audit set is counted, a corresponding first connection node is generated, all the to-be-audited terahertz data in the first audit set are connected based on the first connection node, and a first audit data chain is obtained;

[0014] data whose spectral feature values are less than or equal to corresponding threshold values are classified into a second audit set, the number of to-be-audited terahertz data in the second audit set is counted, a corresponding second connection node is generated, all the to-be-audited terahertz data in the second audit set are connected based on the second connection node, and a second audit data chain is obtained;

[0015] a split node is determined, and tail to-be-audited terahertz data of the first audit data chain and head to-be-audited terahertz data of the second audit data chain are integrated according to the split node, and the to-be-audited terahertz data chain is obtained.

[0016] Further, when the integrity of the to-be-audited terahertz data chain is verified, the method further includes:

[0017] the processing unit calculates a real-time hash value of the to-be-audited terahertz data chain, compares the real-time hash value with a historical hash value generated when the data chain is generated, and judges the integrity of the to-be-audited terahertz data chain according to a comparison result;

[0018] when the real-time hash value is the same as the historical hash value, the processing unit determines that the data of the to-be-audited terahertz data chain is complete;

[0019] when the real-time hash value is different from the historical hash value, the processing unit determines that the data of the to-be-audited terahertz data chain is incomplete.

[0020] Further, when the data of the to-be-audited terahertz data chain is determined to be complete, the processing unit determines a use score of the to-be-audited terahertz data chain, and the method further includes:

[0021] The average frequency of the to-be-audited terahertz data chain is collected, the average frequency is compared with a first average frequency and a second average frequency, and a use score of the to-be-audited terahertz data chain is determined according to a comparison result; wherein the first average frequency is less than the second average frequency;

[0022] When the average frequency is less than or equal to the first average frequency, it is determined that the use score of the to-be-audited terahertz data chain is a first use score;

[0023] When the average frequency is greater than the first average frequency and less than or equal to the second average frequency, it is determined that the use score of the to-be-audited terahertz data chain is a second use score;

[0024] When the average frequency is greater than the second average frequency, it is determined that the use score of the to-be-audited terahertz data chain is a third use score;

[0025] Wherein, the second use score is greater than the first use score, and the third use score is greater than the second use score.

[0026] Further, when determining the initial recommended weight of the to-be-audited terahertz data chain according to the use score, it includes:

[0027] A use score threshold is obtained, and a ratio of the use score to the use score is calculated, denoted as a score ratio;

[0028] When the score ratio is greater than 0 and less than or equal to 0.5, it is determined that the initial recommended weight of the to-be-audited terahertz data chain is a first recommended weight;

[0029] When the score ratio is greater than 0.5 and less than or equal to 1, it is determined that the initial recommended weight of the to-be-audited terahertz data chain is a second recommended weight;

[0030] When the score ratio is greater than 1, it is determined that the initial recommended weight of the to-be-audited terahertz data chain is a third recommended weight;

[0031] Wherein, the second recommended weight is greater than the first recommended weight, and the third recommended weight is greater than the second recommended weight.

[0032] Further, when determining whether to adjust the initial recommended weight according to the comprehensive weight influence value, it includes:

[0033] The comprehensive weight influence value is compared with a comprehensive weight influence value threshold, and whether to adjust the initial recommended weight is determined according to a comparison result;

[0034] When the comprehensive weight influence value is greater than the comprehensive weight influence value threshold, the judging unit determines that the initial recommendation weight needs to be adjusted.

[0035] When the comprehensive weight influence value is less than or equal to the comprehensive weight influence value threshold, the judging unit determines that the initial recommendation weight does not need to be adjusted.

[0036] Further, when the initial recommendation weight and the comprehensive weight influence value are taken as a feature vector and compared with a historical recommendation scheme, the initial recommendation weight is adjusted according to an adjustment coefficient determined according to a comparison result, and a final recommendation weight is obtained, the method comprises the following steps:

[0037] The similarity of each historical feature vector in the historical recommendation scheme and the feature vector is calculated respectively.

[0038] When there is data in the historical recommendation scheme with a similarity greater than a similarity threshold to the feature vector, a historical adjustment coefficient corresponding to the maximum similarity is selected as the adjustment coefficient to adjust the initial recommendation weight.

[0039] When the similarity of each historical feature vector in the historical recommendation scheme and the feature vector is less than or equal to the similarity threshold, a historical adjustment coefficient corresponding to the maximum similarity is selected as an initial adjustment coefficient, a compensation coefficient is determined according to the difference between the maximum similarity and the similarity threshold to compensate the initial adjustment coefficient, and the initial recommendation weight is adjusted by the adjustment coefficient after compensation.

[0040] Further, when the compensation coefficient is determined according to the difference between the maximum similarity and the similarity threshold to compensate the initial adjustment coefficient, the method comprises the following steps:

[0041] The difference between the maximum similarity and the similarity threshold is obtained, denoted as a similarity difference value, the compensation coefficient is in a proportional relationship with the similarity difference value, and the compensation coefficient takes a value range of (0, 1).

[0042] On the other hand, the application further provides a user review recommendation method of terahertz data, which is applied to a user review recommendation system of terahertz data.

[0043] Compared with the prior art, the beneficial effects of the present application are that the user audit recommendation system for terahertz data provided by the present application realizes comprehensive audit and intelligent recommendation of the terahertz data to be audited through the cooperative work of the acquisition unit, the processing unit, the judgment unit, the adjustment unit and the execution unit. The acquisition unit is responsible for the preliminary collection and processing of data, and a structured terahertz data chain to be audited is constructed by comparing the spectral characteristic value with the characteristic value threshold. The processing unit further verifies the integrity of the data chain, and determines the use score and the initial recommendation weight according to the quality of the data chain. This ensures that only high-quality data will be recommended to the user, thereby improving the user experience and the credibility of the system. The judgment unit collects the weight influence value of the data source and calculates the comprehensive weight influence value, which provides a basis for the adjustment of the initial recommendation weight. This takes into account the importance and influence of different data sources, so that the recommendation result is more in line with the actual needs of the user. When the judgment unit determines that the initial recommendation weight needs to be adjusted, the adjustment unit plays a role, taking the initial recommendation weight and the comprehensive weight influence value as a feature vector and comparing it with the historical recommendation scheme, so as to determine the adjustment coefficient and obtain the final recommendation weight. Finally, the execution unit pushes the terahertz data chain to be audited to the user interface based on the final recommendation weight. This step realizes the complete process from data collection to recommendation display, and provides efficient and convenient data audit and recommendation services for the user. The whole system structure is clear and the function is perfect, which can effectively improve the audit efficiency and recommendation accuracy of the terahertz data. BRIEF DESCRIPTION OF DRAWINGS

[0044] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not intended to limit the present application thereto. Moreover, the use of the same reference symbols in different drawings indicates similar or identical items.

[0045] Figure 1 The structural block diagram of the user audit recommendation system for terahertz data provided by the embodiment of the present application. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0047] Reference Figure 1As shown, in some embodiments of the present application, the present embodiment provides a user review recommendation system for terahertz data, comprising:

[0048] A collection unit configured to collect terahertz data to be reviewed from different data sources, obtain the spectral feature value and data type information of each terahertz data to be reviewed, compare the spectral feature value of each terahertz data to be reviewed with the corresponding feature value threshold, and construct all the terahertz data to be reviewed into a terahertz data chain to be reviewed according to the comparison result;

[0049] A processing unit configured to verify the integrity of the terahertz data chain to be reviewed; when the processing unit determines that the data of the terahertz data chain to be reviewed is complete, determine the use score of the terahertz data chain to be reviewed, and determine the initial recommendation weight of the terahertz data chain to be reviewed according to the use score;

[0050] A judgment unit configured to control the collection unit to collect the weight influence value of all the data sources, calculate the comprehensive weight influence value, and determine whether to adjust the initial recommendation weight according to the comprehensive weight influence value;

[0051] An adjustment unit configured to, when it is determined that the initial recommendation weight is to be adjusted, compare the initial recommendation weight and the comprehensive weight influence value as a feature vector with a historical recommendation scheme, adjust the initial recommendation weight according to the comparison result to obtain an adjustment coefficient, and obtain a final recommendation weight;

[0052] An execution unit configured to push the terahertz data chain to be reviewed to a user interface based on the final recommendation weight.

[0053] In some embodiments of the present application, different data sources have different weight influence values, and the data sources include but are not limited to laboratory equipment, sensor networks, remote databases, etc. The weight influence value is a weighted sum of the weight influence values of different data sources.

[0054] It can be understood that the user review recommendation system for terahertz data provided by the embodiment realizes comprehensive review and intelligent recommendation of the terahertz data to be reviewed through the cooperative work of the acquisition unit, the processing unit, the judgment unit, the adjustment unit and the execution unit. The acquisition unit is responsible for the preliminary collection and processing of data, and a structured terahertz data chain to be reviewed is constructed by comparing the spectral characteristic value with the characteristic value threshold. The processing unit further verifies the integrity of the data chain, and determines the use score and the initial recommendation weight according to the quality of the data chain. This ensures that only high-quality data will be recommended to the user, thereby improving the user experience and the credibility of the system. The judgment unit collects the weight influence value of the data source and calculates the comprehensive weight influence value, which provides a basis for adjusting the initial recommendation weight. This takes into account the importance and influence of different data sources, so that the recommendation result is more in line with the actual needs of the user. When the judgment unit determines that the initial recommendation weight needs to be adjusted, the adjustment unit plays a role, taking the initial recommendation weight and the comprehensive weight influence value as a feature vector and comparing it with the historical recommendation scheme to determine the adjustment coefficient and obtain the final recommendation weight. Finally, the execution unit pushes the terahertz data chain to be reviewed to the user interface based on the final recommendation weight. This step realizes the complete process from data collection to recommendation display, providing efficient and convenient data review and recommendation services for users. The whole system structure is clear and the function is perfect, which can effectively improve the review efficiency and recommendation accuracy of terahertz data.

[0055] Specifically, the spectral characteristic values include frequency, amplitude, phase and bandwidth.

[0056] Specifically, when all the terahertz data to be reviewed are constructed into a terahertz data chain to be reviewed according to the comparison results, it includes:

[0057] Data with spectral characteristic values greater than the corresponding characteristic value threshold are classified into a first review set, the number of terahertz data to be reviewed in the first review set is counted, and a corresponding first connection node is generated. Based on the first connection node, all the terahertz data to be reviewed in the first review set are connected to obtain a first review data chain.

[0058] Data with spectral characteristic values less than or equal to the corresponding characteristic value threshold are classified into a second review set, the number of terahertz data to be reviewed in the second review set is counted, and a corresponding second connection node is generated. Based on the second connection node, all the terahertz data to be reviewed in the second review set are connected to obtain a second review data chain.

[0059] determining a split node, and integrating the tail of the first audit data chain and the head of the second audit data chain according to the split node, to obtain the audit data chain.

[0060] It can be understood that by intelligently dividing the audit data and constructing multiple data chains, precise management of different data types is achieved. By comparing the spectral feature value with the spectral feature value threshold, the data is divided into two categories of high priority and low priority, which not only optimizes the order of data audit and ensures the rational use of resources. The data in the first audit set (i.e. high priority data) can be processed preferentially, while the data in the second audit set (i.e. low priority data) is processed when the resources are relaxed, thereby avoiding the delay of high priority data audit. Through the design of connection nodes and split nodes, the ordered and efficient audit of data is achieved, avoiding the confusion or conflict of data in the audit process, ensuring the integrity and smoothness of the data chain. It can dynamically adapt to different data audit needs and real-time environmental conditions, thereby improving the stability, reliability and efficiency of data audit. When processing a large amount of data, it can be flexibly adjusted to avoid resource waste and processing bottlenecks.

[0061] Specifically, when verifying the integrity of the audit data chain, it includes:

[0062] The processing unit calculates the real-time hash value of the audit data chain, compares the real-time hash value with the historical hash value when the data chain is generated, and judges the integrity of the audit data chain according to the comparison result;

[0063] When the real-time hash value is the same as the historical hash value, the processing unit determines that the data of the audit data chain is complete;

[0064] When the real-time hash value is different from the historical hash value, the processing unit determines that the data of the audit data chain is incomplete.

[0065] It can be understood that by comparing the real-time hash value with the historical hash value, the system can accurately identify whether the data chain has been tampered with or damaged during transmission or processing. This double verification mechanism ensures the integrity and consistency of the data, which is a key step to improve the reliability and security of the system. When the data chain is determined to be complete, the system will further determine its use score and initial recommendation weight according to the quality of the data chain, which further strengthens the strictness and accuracy of data audit. The whole processing process is efficient and rigorous, fully demonstrating the advanced nature and practicality of the system in the field of terahertz data audit and recommendation.

[0066] Specifically, when determining the data integrity of the to-be-audited terahertz data chain, the processing unit determines the usage score of the to-be-audited terahertz data chain, comprising:

[0067] The average frequency of the to-be-audited terahertz data chain is collected, and the average frequency is compared with the first average frequency and the second average frequency, and the usage score of the to-be-audited terahertz data chain is determined according to the comparison result; wherein the first average frequency is less than the second average frequency;

[0068] When the average frequency is less than or equal to the first average frequency, the usage score of the to-be-audited terahertz data chain is determined as the first usage score;

[0069] When the average frequency is greater than the first average frequency and less than or equal to the second average frequency, the usage score of the to-be-audited terahertz data chain is determined as the second usage score;

[0070] When the average frequency is greater than the second average frequency, the usage score of the to-be-audited terahertz data chain is determined as the third usage score;

[0071] Wherein, the second usage score is greater than the first usage score, and the third usage score is greater than the second usage score.

[0072] It can be understood that by comparing the average frequency with the preset frequency threshold, the system can quantitatively evaluate the quality of the data chain. This scoring mechanism is not only simple and easy to implement, but also can intuitively reflect the advantages and disadvantages of the data chain, providing an important basis for subsequent determination of the recommended weight. The setting of the first average frequency and the second average frequency fully considers the differences between different data chains, making the scoring result more in line with the actual situation. According to the different intervals of the average frequency, different usage scores are given to the data chain, ensuring that high-quality data chains can obtain higher scores and more preferential recommendation opportunities. This combination of scoring and recommendation not only improves the intelligent level of the system, but also enhances the satisfaction of user experience.

[0073] Specifically, according to the usage score, the initial recommended weight of the to-be-audited terahertz data chain is determined, comprising:

[0074] Obtain a usage score threshold, and calculate the ratio of the usage score to the usage score, denoted as score ratio;

[0075] When the score ratio is greater than 0 and less than or equal to 0.5, the initial recommended weight of the to-be-audited terahertz data chain is determined as the first recommended weight;

[0076] determining that the initial recommended weight of the terahertz data chain to be audited is a second recommended weight when the score ratio is greater than 0.5 and less than or equal to 1;

[0077] determining that the initial recommended weight of the terahertz data chain to be audited is a third recommended weight when the score ratio is greater than 1;

[0078] wherein the second recommended weight is greater than the first recommended weight, and the third recommended weight is greater than the second recommended weight.

[0079] It can be understood that, by comparing the score ratio with the use score threshold, the system can more finely divide the recommended weight of the data chain. This hierarchical setting not only takes into account the differences in data chain quality, but also ensures that the allocation of recommended weight is more reasonable and fair. The setting of the first recommended weight, the second recommended weight and the third recommended weight provides different recommended opportunities for data chains of different qualities, ensuring the priority display of high-quality data chains and giving low-quality data chains certain display space, thereby meeting user needs while also promoting data diversity and richness.

[0080] Specifically, when determining whether to adjust the initial recommended weight according to the comprehensive weight influence value, the method comprises:

[0081] comparing the comprehensive weight influence value with a comprehensive weight influence value threshold, and determining whether to adjust the initial recommended weight according to the comparison result;

[0082] when the comprehensive weight influence value is greater than the comprehensive weight influence value threshold, the determination unit determines that the initial recommended weight needs to be adjusted;

[0083] when the comprehensive weight influence value is less than or equal to the comprehensive weight influence value threshold, the determination unit determines that the initial recommended weight does not need to be adjusted.

[0084] It can be understood that, by comparing the comprehensive weight influence value with the preset threshold, the system can intelligently identify the importance of different data sources for the recommendation of the terahertz data chain to be audited. This judgment mechanism not only improves the accuracy of the recommendation, but also ensures that the recommended result is more in line with the actual needs of the user.

[0085] Specifically, when the initial recommended weight and the comprehensive weight influence value are compared with historical recommended schemes as feature vectors, the initial recommended weight is adjusted according to the adjustment coefficient determined according to the comparison result, and the final recommended weight is obtained, the method comprises:

[0086] respectively calculating the similarity of each historical feature vector in the historical recommended scheme and the feature vector;

[0087] When there is data in the historical recommendation scheme that has a similarity greater than a similarity threshold to the feature vector, the historical adjustment coefficient corresponding to the maximum similarity is selected as the adjustment coefficient to adjust the initial recommendation weight;

[0088] When the similarity of each historical feature vector in the historical recommendation scheme to the feature vector is less than or equal to a similarity threshold, the historical adjustment coefficient corresponding to the maximum similarity is selected as an initial adjustment coefficient, a compensation coefficient is determined according to the difference between the maximum similarity and the similarity threshold to compensate for the initial adjustment coefficient, and the adjustment coefficient after compensation is used as the adjustment coefficient to adjust the initial recommendation weight.

[0089] It can be understood that by comparing the feature vector with the historical recommendation scheme, the system can find the historical adjustment scheme that is closest to the current situation, thereby quickly determining the appropriate adjustment coefficient. When there is historical data with high similarity, the adjustment coefficient of the historical data is directly used, which not only saves computing resources, but also ensures the accuracy and reasonableness of the adjustment. When there is no highly similar historical data, the system fine-tunes the initial adjustment coefficient by introducing a compensation coefficient to ensure that the determination of the final recommendation weight is more in line with the actual situation. This flexible adjustment mechanism not only embodies the intelligent characteristics of the system, but also ensures the stability and reliability of the recommendation result. The entire determination process of the recommendation weight not only considers the quality of the data chain itself, but also takes into account the importance and influence of different data sources, thereby ensuring the comprehensiveness and accuracy of the recommendation result.

[0090] Specifically, when the compensation coefficient is determined according to the difference between the maximum similarity and the similarity threshold to compensate for the initial adjustment coefficient, it includes:

[0091] The difference between the maximum similarity and the similarity threshold is obtained, denoted as a similarity difference, the compensation coefficient is in a positive relationship with the similarity difference, and the compensation coefficient has a value range of (0, 1).

[0092] It can be understood that by introducing the similarity difference to determine the compensation coefficient, the system can more finely adjust the recommendation weight. When the difference between the maximum similarity and the similarity threshold is large, it means that there is a large difference between the current situation and the historical recommendation scheme, and a large compensation coefficient is needed to adjust the initial adjustment coefficient to ensure the accuracy of the final recommendation weight. When the difference is small, it means that the current situation is close to the historical recommendation scheme, and the compensation coefficient needed is relatively small. This method of dynamically adjusting the compensation coefficient according to the similarity difference not only ensures the flexibility of the adjustment, but also ensures the stability and reliability of the recommendation result.

[0093] In another aspect, the present application further provides a user review recommendation method of terahertz data, applied to a user review recommendation system of terahertz data.

[0094] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can be embodied in the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) having computer usable program code embodied therein.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing device, generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0096] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0097] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A user review and recommendation system using terahertz data, characterized in that, include: The acquisition unit is configured to acquire terahertz data to be reviewed from different data sources, obtain the spectral feature value and data type information of each terahertz data to be reviewed, compare the spectral feature value of each terahertz data to be reviewed with the corresponding feature value threshold, and construct a terahertz data chain to be reviewed from all the terahertz data to be reviewed based on the comparison results. The processing unit is configured to verify the integrity of the terahertz data chain to be audited; when the processing unit determines that the data of the terahertz data chain to be audited is complete, it determines the usage score of the terahertz data chain to be audited, and determines the initial recommendation weight of the terahertz data chain to be audited based on the usage score. The judgment unit is configured to control the acquisition unit to collect the weight influence values ​​of all the data sources, calculate the comprehensive weight influence value, and determine whether to adjust the initial recommendation weight based on the comprehensive weight influence value; The adjustment unit is configured to, when it is determined that the initial recommendation weight should be adjusted, compare the initial recommendation weight and the comprehensive weight influence value as feature vectors with historical recommendation schemes, determine the adjustment coefficient based on the comparison result, adjust the initial recommendation weight, and obtain the final recommendation weight. The execution unit is configured to push the pending terahertz data chain to the user interface based on the final recommendation weight; The spectral characteristics include: frequency, amplitude, phase, and bandwidth; When constructing a terahertz data chain based on the comparison results of all the terahertz data to be audited, it includes: Data whose spectral feature values ​​are greater than the corresponding feature value thresholds are included in the first audit set. The number of terahertz data to be audited in the first audit set is counted, and a corresponding first connection node is generated. Based on the first connection node, all the terahertz data to be audited in the first audit set are connected to obtain the first audit data chain. Data whose spectral feature values ​​are less than or equal to the corresponding feature value thresholds are assigned to the second audit set. The number of terahertz data to be audited in the second audit set is counted, and a corresponding second connection node is generated. Based on the second connection node, all the terahertz data to be audited in the second audit set are connected to obtain the second audit data chain. Determine the segmentation node, and integrate the tail terahertz data to be reviewed of the first review data chain and the first terahertz data to be reviewed of the second review data chain according to the segmentation node to obtain the terahertz data chain to be reviewed.

2. The terahertz data user review and recommendation system according to claim 1, characterized in that, Verifying the integrity of the terahertz data link to be audited includes: The processing unit calculates the real-time hash value of the terahertz data chain to be audited, compares the real-time hash value with the historical hash value when the data chain was generated, and judges the integrity of the terahertz data chain to be audited based on the comparison result. When the real-time hash value is the same as the historical hash value, the processing unit determines that the data of the terahertz data chain to be audited is complete; When the real-time hash value is different from the historical hash value, the processing unit determines that the data of the terahertz data chain to be audited is incomplete.

3. The terahertz data user review and recommendation system according to claim 2, characterized in that, When determining the data integrity of the terahertz data link to be audited, the processing unit, when determining the usage score of the terahertz data link to be audited, includes: The average frequency of the terahertz data link to be audited is collected, and the average frequency is compared with a first average frequency and a second average frequency. The usage score of the terahertz data link to be audited is determined based on the comparison result; wherein, the first average frequency is less than the second average frequency. When the average frequency is less than or equal to the first average frequency, the usage score of the terahertz data link to be audited is determined to be the first usage score; When the average frequency is greater than the first average frequency and less than or equal to the second average frequency, the usage score of the terahertz data link to be audited is determined to be the second usage score. When the average frequency is greater than the second average frequency, the usage score of the terahertz data link to be audited is determined to be the third usage score; The second usage score is greater than the first usage score, and the third usage score is greater than the second usage score.

4. The terahertz data user review and recommendation system according to claim 3, characterized in that, When determining the initial recommendation weight of the terahertz data chain to be reviewed based on the usage score, the following are included: Obtain the usage rating threshold and calculate the ratio of the usage rating to the usage score, denoted as the rating ratio; When the score ratio is greater than 0 and less than or equal to 0.5, the initial recommendation weight of the terahertz data chain to be reviewed is determined to be the first recommendation weight. When the score ratio is greater than 0.5 and less than or equal to 1, the initial recommendation weight of the terahertz data chain to be reviewed is determined to be the second recommendation weight. When the score ratio is greater than 1, the initial recommendation weight of the terahertz data chain to be reviewed is determined to be the third recommendation weight. Wherein, the second recommendation weight is greater than the first recommendation weight, and the third recommendation weight is greater than the second recommendation weight.

5. The terahertz data user review and recommendation system according to claim 1, characterized in that, When determining whether to adjust the initial recommendation weight based on the comprehensive weight impact value, the following are included: The comprehensive weight impact value is compared with the comprehensive weight impact value threshold, and the initial recommendation weight is adjusted based on the comparison result. When the comprehensive weight impact value is greater than the comprehensive weight impact value threshold, the judgment unit determines that the initial recommendation weight needs to be adjusted. When the comprehensive weight influence value is less than or equal to the comprehensive weight influence value threshold, the judgment unit determines that there is no need to adjust the initial recommendation weight.

6. The terahertz data user review and recommendation system according to claim 1, characterized in that, When comparing the initial recommendation weights and the combined weight impact value as feature vectors with historical recommendation schemes, and adjusting the initial recommendation weights based on the comparison results using adjustment coefficients, and obtaining the final recommendation weights, the process includes: Calculate the similarity between each historical feature vector in the historical recommendation scheme and the feature vector; When there is data in the historical recommendation scheme that has a similarity greater than the similarity threshold with the feature vector, the historical adjustment coefficient corresponding to the maximum similarity is selected as the adjustment coefficient to adjust the initial recommendation weight; When the similarity between each historical feature vector in the historical recommendation scheme and the feature vector is less than or equal to the similarity threshold, the historical adjustment coefficient corresponding to the maximum similarity is selected as the initial adjustment coefficient. A compensation coefficient is determined based on the difference between the maximum similarity and the similarity threshold to compensate the initial adjustment coefficient. The compensated adjustment coefficient is then used as the adjustment coefficient to adjust the initial recommendation weight.

7. The terahertz data user review and recommendation system according to claim 6, characterized in that, When compensating the initial adjustment coefficient based on the difference between the maximum similarity and the similarity threshold, the compensation coefficient is determined as follows: The difference between the maximum similarity and the similarity threshold is obtained and denoted as the similarity difference. The compensation coefficient is proportional to the similarity difference and the value range of the compensation coefficient is (0, 1).

8. A user review and recommendation method for terahertz data, applied to the user review and recommendation system for terahertz data as described in any one of claims 1-7.

Images