Tamper identification method and system based on weighing data of electronic scale

Abstract

The invention discloses a tampering identification method and system based on weighing data of an electronic scale, relates to the technical field of tampering identification, and is used for solving the problems of low identification efficiency and unnecessary resource loss caused by incapability of rapidly identifying tampering. Collecting the time difference between the uploading time and the actual weighing time, the difference value of the content size of the uploaded data packet, the integrity of data uploading and the number of continuous failure times of identity verification, establishing a data analysis model, obtaining a hidden danger evaluation coefficient, comparing the hidden danger evaluation coefficient with a preset hidden danger threshold, determining the tampering probability, and determining the tampering judgment result according to the tampering probability. Determining a hidden danger monitoring result according to the similarity of electric signals converted from the weight of the same object by the sensor, detecting a hidden danger evaluation coefficient corresponding to the hidden danger monitoring result, and formulating a group of fuzzy rules to perform fuzzy reasoning according to the transmission data signature safety corresponding to the identification point and the transmission data signature calculation efficiency corresponding to the identification point; therefore, the recognition efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tampering identification, and more specifically, to a tampering identification method and system based on electronic scale weighing data. Background Art

[0002] Electronic scales are widely used in many fields such as commercial retail, industrial production, and logistics management. They are devices that use electronic sensors and digital processing technologies for accurate weighing. Different from traditional mechanical scales, electronic scales convert the weight of an object into an electrical signal through sensors and display it on a digital screen after processing. They have higher accuracy, stability, and convenience, and the authenticity and accuracy of their weighing data are directly related to the fairness of economic transactions.

[0003] The prior art has the following deficiencies:

[0004] Currently, the tampering method is to embed a cheating backdoor in the application program. When cheating, it enters the cheating state by inputting passwords, key combinations, etc., thus changing the measurement result. However, the existing anti-tampering is usually based on the identification of the monitoring module and regular monitoring, which has a long lag period and cannot quickly identify tampering, resulting in low identification efficiency and unnecessary resource losses. Therefore, a tampering identification method and system based on electronic scale weighing data are proposed.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a tampering identification method and system based on electronic scale weighing data, and solve the problems proposed in the above background art by using different product inspection methods.

[0007] To achieve the above object, the present invention provides the following technical solution. A tampering identification method based on electronic scale weighing data includes:

[0008] S1: Collect the feature information of the electronic scale and the data integrity feature information, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the upload data packet content, the integrity of data upload, and the number of consecutive authentication failures.

[0009] S2: Obtain the time difference between the upload time and the actual weighing time, the difference in the size of the upload data packet content, the integrity of data upload, and the number of consecutive authentication failures, establish a data analysis model, and obtain a hidden danger assessment coefficient.

[0010] S3: Obtain the hidden danger assessment coefficient, compare it with the preset hidden danger threshold to obtain a comparison result, determine the probability of tampering based on different comparison results, and determine the hidden danger monitoring result based on the similarity of the electrical signals converted by the sensor for the same object's weight;

[0011] S4: Obtain the hidden danger monitoring result, detect the hidden danger assessment coefficient corresponding to the hidden danger monitoring result, obtain the identification point corresponding to the hidden danger assessment coefficient, and collect the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point;

[0012] S5: Obtain the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point, substitute them into fuzzy logic for fuzzy reasoning to obtain the hidden danger degree result.

[0013] In a preferred embodiment, the electronic scale characteristic information includes the time difference between the upload time and the actual weighing time and the difference in the size of the upload data packet content; the data integrity characteristic information includes the integrity of data upload and the number of consecutive authentication failures;

[0014] By defining the actual weighing time point and the data upload time point, and then subtracting the actual weighing time point from the data upload time point, the time difference between the upload time and the actual weighing time is obtained ; where i is the i-th identification point;

[0015] By defining the actual size of the upload data packet and the expected size of the upload data packet, and then taking the absolute value of the difference between the actual size of the upload data packet and the expected size of the upload data packet to obtain the difference in the size of the upload data packet content ;

[0016] The number of data fields successfully uploaded is marked by calculating the number of data fields with consistent checksum of the upload data packet, and the total number of data fields to be uploaded is counted. The ratio of the number of data fields successfully uploaded to the total number of data fields to be uploaded is calculated to obtain the integrity of data upload ;

[0017] By preferentially setting a time window, through the preset time window, if the time difference between two failure events is less than the set time window value, it is recorded as a consecutive failure. The system will maintain the count of consecutive failures until the consecutive failure event ends. Based on the count of consecutive failures, the number of consecutive authentication failures is obtained .

[0018] In a preferred embodiment, obtain the time difference between the upload time and the actual weighing time, the difference in the size of the upload data packet content, the integrity of data upload, and the number of consecutive authentication failures to establish a data analysis model and generate a hidden danger assessment coefficient , and the formula based on it is: ;

[0019] Wherein, is the hidden danger assessment coefficient, , , and are respectively the time difference between the upload time and the actual weighing time , the difference in the size of the uploaded data packet content , the integrity of data upload and the preset proportional coefficients of the number of consecutive authentication failures, and , , and are all greater than 0.

[0020] In a preferred embodiment, after obtaining the hidden danger assessment coefficient, the hidden danger assessment coefficient is compared and analyzed with the continuously iterated hidden danger threshold;

[0021] If the hidden danger assessment coefficient is greater than or equal to the hidden danger threshold, the current electronic scale weighing data is marked as hidden danger data, and a risk signal is generated;

[0022] If the hidden danger assessment coefficient is less than the hidden danger threshold, the current electronic scale weighing data is marked as safe data, and a safety signal is generated.

[0023] In a preferred embodiment, multiple calculations are performed to obtain multiple hidden danger assessment coefficients and their comparison results. The number of times marked as hidden danger data and the corresponding hidden danger assessment coefficient values are statistically counted, and then the total number of all hidden danger assessment coefficients and the corresponding hidden danger assessment coefficient values are statistically counted and substituted into the formula for calculation to obtain the probability of tampering;

[0024] The specific formula is: ;

[0025] Wherein, is the probability of tampering, n is the total number of hidden danger assessment coefficients, q is the number of times marked as hidden danger data, is the hidden danger assessment coefficient calculated for the first time, is the hidden danger assessment coefficient calculated for the second time, is the hidden danger assessment coefficient calculated for the qth time, is the hidden danger assessment coefficient calculated for the nth time.

[0026] In a preferred embodiment, the same object is preferentially identified by the object number set for the object, and the corresponding electrical signal is obtained. The frequency components of the signal are extracted from the electrical signal through Fourier transform as feature vectors, and the cosine similarity is used to calculate the similarity of the electrical signals converted by the sensor from the weights of the same objects;

[0027] The similarity of the electrical signals converted by the sensor from the weights of the same objects is weighted and averaged with the probability of tampering to obtain a tampering monitoring coefficient, which is compared with a preset monitoring threshold. If the tampering monitoring coefficient is greater than or equal to the monitoring threshold, it indicates that tampering exists currently, and an alarm signal is generated; if the tampering monitoring coefficient is less than the monitoring threshold, it indicates that there are some potential hazards currently, and a marking signal is generated;

[0028] The alarm signal is screened out, and the marking signal is calibrated as the hidden danger monitoring result.

[0029] In a preferred embodiment, by determining the signature algorithm type used for the data packet corresponding to each identification point, a weighted average calculation is set by combining the algorithm type and the key length to obtain the security of the transmission data signature corresponding to the identification point;

[0030] Through comprehensive calculation and analysis of the signature generation time and the signature verification time, the calculation efficiency of the transmission data signature corresponding to the identification point is obtained.

[0031] In a preferred embodiment, the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point are defined as input variables, and they are respectively divided into different fuzzy sets;

[0032] The result of the hidden danger degree is defined as an output variable, and it is divided into a fuzzy set;

[0033] Fuzzy rules are formulated to describe the influence of the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point on the result of the hidden danger degree;

[0034] According to the fuzzy rules, fuzzy reasoning is performed to determine the result of the hidden danger degree.

[0035] A tampering identification system based on electronic scale weighing data includes a data acquisition module, a data analysis module, a tampering analysis module, and a hidden danger assessment module;

[0036] The data acquisition module is used to collect the electronic scale feature information and the data integrity feature information, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of the data upload, and the number of consecutive authentication failures, and send them to the data analysis module;

[0037] The data analysis module is used to establish a data analysis model based on the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures, obtain a hidden danger assessment coefficient, and send it to the tampering analysis module;

[0038] The tampering analysis module is used to obtain the hidden danger assessment coefficient, compare it with a preset hidden danger threshold to obtain a comparison result, determine the probability of tampering based on different comparison results, and determine the hidden danger monitoring result based on the similarity of the electrical signals converted by the sensor for the same object, and send it to the hidden danger assessment module;

[0039] The hidden danger assessment module is used to obtain the hidden danger monitoring result, detect the hidden danger assessment coefficient corresponding to the hidden danger monitoring result, obtain the identification point corresponding to the hidden danger assessment coefficient, collect the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point, and substitute them into fuzzy logic for fuzzy reasoning to obtain the hidden danger degree result.

[0040] The technical effects and advantages of the present invention:

[0041] 1. By collecting the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures, the present invention establishes a data analysis model, obtains a hidden danger assessment coefficient, compares it with a preset hidden danger threshold to obtain a comparison result, determines the probability of tampering based on different comparison results, and determines the hidden danger monitoring result based on the similarity of the electrical signals converted by the sensor for the same object, enhancing the anti-tampering ability of the electronic scale, and performing real-time monitoring and early warning, quickly identifying tampering, improving the identification efficiency, and reducing unnecessary resource losses.

[0042] 2. By obtaining the hidden danger monitoring result, detecting the hidden danger assessment coefficient corresponding to the hidden danger monitoring result, obtaining the identification point corresponding to the hidden danger assessment coefficient, collecting and formulating a set of fuzzy rules for fuzzy reasoning based on the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point, and determining the hidden danger degree result, the present invention can more deeply excavate the hidden data and hidden risks of the weighing data of the electronic scale, improving the accuracy of the weighing data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a method flow chart of a tampering identification method based on the weighing data of an electronic scale according to the present invention.

[0044] Figure 2 It is a module schematic diagram of a tampering identification system based on the weighing data of an electronic scale according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment 1

[0047] Please refer to Figure 1 , a method for identifying tampering with weighing data of an electronic scale, and the specific operation process is as follows:

[0048] S1: Collect the feature information of the electronic scale and the data integrity feature information, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures;

[0049] Among them, normalization processing is a common method of data preprocessing, which is used to convert data of different scales or ranges to a unified scale, so that the influence of each feature on subsequent analysis or model training is more balanced. In the analysis of electronic scale data, normalization processing helps to eliminate the dimensional difference between different features and ensure the balanced contribution of each feature to the model;

[0050] Specifically, the normalization method is through Z-score standardization, and the specific formula is expressed as: ;

[0051] In the formula, is the original data after normalization, is the original data, is the mean of the original data, is the standard deviation of the original data;

[0052] Among them, the expression of the original data includes the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures. The above formula is used for normalization processing, which will not be elaborated here;

[0053] Specifically, the feature information of the electronic scale includes the time difference between the upload time and the actual weighing time and the difference in the size of the uploaded data packet content; the data integrity feature information includes the integrity of data upload and the number of consecutive authentication failures;

[0054] Among them, the time difference between the upload time and the actual weighing time refers to the difference between the time point when the electronic scale uploads data and the time point when the actual weighing operation occurs. The time difference can be used to evaluate whether there is a delay, abnormality, or possibility of data tampering in the data upload of the electronic scale. Its acquisition logic is to define the actual weighing time point and the data upload time point, and then subtract the actual weighing time point from the data upload time point to obtain the time difference between the upload time and the actual weighing time. ; where i is the i-th recognition point;

[0055] Specifically, the actual weighing time point is the time when the electronic scale actually measures and records the weighing data (specifically, when it is automatically recorded by the sensors and control system of the electronic scale), and the data upload time point is the time when the electronic scale uploads the weighing data to the preset server through the communication module. Specifically, the preset server is not limited, but is set by the experimenter according to the actual monitoring intensity and will not be elaborated here;

[0056] It should be noted that the setting and interval of the recognition points are obtained by the experimenter according to the tampering frequency and correct recognition probability of the historical weighing data of the electronic scale, and will not be elaborated here;

[0057] The difference in the content size of the upload data packet refers to the difference between the actual size and the expected size of the uploaded electronic scale data packet, which is used to detect whether the uploaded data has an abnormality. Its acquisition logic is to define the actual size of the uploaded data packet and the expected size of the uploaded data packet, and then obtain the difference in the content size of the upload data packet by taking the absolute value of subtracting the expected size of the uploaded data packet from the actual size of the uploaded data packet. ;

[0058] Specifically, the actual size of the uploaded data packet refers to the actual number of bytes of the data packet when the electronic scale uploads. In network communication, each time the electronic scale sends data to the server or cloud, it is transmitted in the form of a data packet, which contains weighing data, timestamp, device information, verification information content, etc., and will not be elaborated here;

[0059] Among them, the expected size of the uploaded data packet is the size estimated according to the data structure and transmission protocol of the electronic scale. The format of the weighing data, and the additional data are timestamp, device ID, sensor data, authentication information, etc., which are not limited here;

[0060] Specifically, if the difference in the content size of the upload data packet is larger, it indicates that there are abnormal situations such as data tampering and data injection during the upload process of the electronic scale. This can identify the traces of tampering when the tampering occurs. Compared with the traditional identification based on the monitoring module and regular monitoring, it avoids a long lag period and enables timely follow-up operations to avoid irreparable resource losses;

[0061] The integrity of data upload refers to whether the data uploaded by the electronic scale is completely and accurately transmitted to the server or the cloud, including all key data, additional information to be transmitted and their integrity. The acquisition logic is to calculate the number of data fields marked as successfully uploaded by the number of consistent checksums of the uploaded data packets, and count the total number of data fields to be uploaded as scheduled. Then, calculate the ratio of the number of successfully uploaded data fields to the total number of data fields to be uploaded as scheduled to obtain the integrity of data upload. ;

[0062] Among them, the checksum of the uploaded data packet is a value obtained by performing mathematical operations on the content of the data packet. Specifically, the sender will calculate the checksum before uploading the data and include it in the data packet. The receiver will then calculate the checksum of the received data packet using the same algorithm and compare it with the checksum provided by the sender. If they are the same, it is recorded as a successfully uploaded data field and the quantity is counted. Then, count the quantity of all uploaded data fields to obtain the total number of data fields to be uploaded as scheduled.

[0063] The number of consecutive authentication failures refers to the number of consecutive authentication failures that occur within a short period of time, focusing on expressing the situation of consecutive authentication failures within a set time window. The acquisition logic is to first set a time window. Through the preset time window, if the time difference between two failure events is less than the set time window value, it is recorded as a consecutive failure. The system will maintain the count of consecutive failures until the consecutive failure event ends. Based on the count of consecutive failures, the number of consecutive authentication failures is obtained. ;

[0064] Among them, the set time window can be the time length of the electronic scale weighing as the time window, or the fixed number of weighings of the electronic scale as the time window. The specific definition of the time window is set by the experimenter according to the specific implementation situation and will not be elaborated here.

[0065] S2: Obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures, establish a data analysis model, and obtain a hidden danger assessment coefficient.

[0066] Among them, the data analysis model refers to a weighted analysis model, and a hidden danger assessment coefficient is generated through weighted calculation.

[0067] Obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures, establish a data analysis model, and generate a hidden danger assessment coefficient , based on the formula: ;

[0068] In the formula, is the hidden danger assessment coefficient, , , as well as The time difference between the upload time and the actual weighing time , upload data packet content size difference , Completeness of data upload and the number of consecutive authentication failures The preset scaling factor of , , as well as All are greater than 0;

[0069] Among them, the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet, the completeness of the data upload, and the number of consecutive identity authentication failures are all digital manifestations that directly express the probability that the current electronic scale weighing data has been tampered with;

[0070] It can be seen from the formula that the higher the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, and the number of consecutive identity authentication failures, the greater the probability that the current electronic scale weighing data has been tampered with, and the higher the hidden danger assessment coefficient. Conversely, the higher the integrity of the data upload, the lower the probability that the current electronic scale weighing data has been tampered with, and the lower the tag assessment coefficient.

[0071] S3: Obtain the hidden danger assessment coefficient and compare it with the preset hidden danger threshold to obtain the comparison result. According to different comparison results, determine the probability of tampering, and determine the hidden danger monitoring result according to the similarity of the electrical signal converted by the sensor from the weight of the same object;

[0072] The logic for obtaining the hidden danger threshold is to collect a set of historical electronic scale weighing data detection, divide the data set into a training set and a test set, set the evaluation index and clustering algorithm, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. Then, adjust the hidden danger threshold according to the performance of the validation set. Therefore, the hidden danger threshold is constantly iterated and updated;

[0073] In the present invention, clustering algorithm is a kind of unsupervised learning algorithm, which is used to divide the weighing data in the data set into marked groups or clusters; the common one is K-means clustering, which divides the weighing data in the data set into K clusters, so that the distance between each weighing data and the center point (center of mass) of the cluster to which it belongs is minimized, and finally the hidden danger risk of the weighing data is measured by the Euclidean distance, so as to set the hidden danger threshold;

[0074] After obtaining the hidden danger assessment coefficient, compare and analyze the hidden danger assessment coefficient with the continuously iterated hidden danger threshold;

[0075] If the hidden danger assessment coefficient is greater than or equal to the hidden danger threshold, mark the current weighing data of the electronic scale as hidden danger data and generate a risk signal;

[0076] If the hidden danger assessment coefficient is less than the hidden danger threshold, mark the current weighing data of the electronic scale as safe data and generate a safety signal;

[0077] Perform multiple calculations to obtain multiple hidden danger assessment coefficients and their comparison results, count the number of times marked as hidden danger data and the corresponding hidden danger assessment coefficient values, then count the total number of all hidden danger assessment coefficients and the corresponding hidden danger assessment coefficient values, and substitute them into the formula for calculation to obtain the probability of tampering;

[0078] The specific formula is: ;

[0079] In the formula, is the probability of tampering, n is the total number of hidden danger assessment coefficients, q is the number of times marked as hidden danger data, is the hidden danger assessment coefficient of the first calculation, is the hidden danger assessment coefficient of the second calculation, is the hidden danger assessment coefficient of the qth calculation, is the hidden danger assessment coefficient of the nth calculation;

[0080] The similarity of the electrical signals converted by the sensor for the same object's weight refers to the similarity of the electrical signals converted by the sensor for the weight measurement of the same object at different times. Its acquisition logic is to first identify the same object through the object number set for the object, obtain the corresponding electrical signal, extract the frequency components of the signal through Fourier transform as the feature vector, and use the cosine similarity calculation to obtain the similarity of the electrical signals converted by the sensor for the same object's weight;

[0081] Among them, setting the object number for the object means assigning a unique identifier to each object to distinguish and identify the same object during multiple weighings, ensuring that the electrical signal data measured by the sensor at different time points can be accurately corresponding to the same object; the specifically set object number can be a unique barcode or QR code, or a radio frequency identification (RFID) tag, etc., which is not limited here;

[0082] Furthermore, for each measured electrical signal (time series data), through the fast Fourier transform, the time-domain signal is converted into a frequency-domain signal;

[0083] The frequency characteristics obtained through Fourier transform are used as feature vectors for the calculation of cosine similarity. The specific calculation formula is: ;

[0084] In the formula, is the similarity of the electrical signals converted by the sensor from the weights of equal objects, is the modulus of the electrical signal measured for the first time for the same object, is the modulus of the electrical signal measured for the second time for the same object, A is the eigenvector of the electrical signal measured for the first time for the same object, and H is the eigenvector of the electrical signal measured for the second time for the same object;

[0085] The similarity of the electrical signals converted by the sensor from the weights of equal objects is weighted and averaged with the probability of tampering to obtain a tampering monitoring coefficient, which is compared with a preset monitoring threshold. If the tampering monitoring coefficient is greater than or equal to the monitoring threshold, it indicates that there is current tampering and an alarm signal is generated; if the tampering monitoring coefficient is less than the monitoring threshold, it indicates that there are some current potential hazards and a marking signal is generated;

[0086] It should be noted that the monitoring threshold is obtained through comprehensive analysis of historical tampering monitoring coefficients and historical tampering frequencies, which will not be elaborated here;

[0087] Specifically, regarding the subsequent operations for generating the alarm signal, it can be to turn off the digital display of the electronic scale or emit an alarm sound, etc. The specific subsequent operations are set by the experimenter and will not be elaborated here;

[0088] The alarm signal is screened out, and the marking signal is calibrated as the potential hazard monitoring result;

[0089] The present invention establishes a data analysis model by collecting the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures, obtains a potential hazard assessment coefficient, compares it with a preset potential hazard threshold to obtain a comparison result, determines the probability of tampering based on different comparison results, and determines the potential hazard monitoring result based on the similarity of the electrical signals converted by the sensor from the weights of equal objects, enhances the anti-tampering ability of the electronic scale, and conducts real-time monitoring and early warning, quickly identifies tampering, improves the identification efficiency, and reduces unnecessary resource losses.

[0090] Embodiment 2

[0091] In Embodiment 1 of the present invention, the time difference between the acquisition upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of data upload, and the number of consecutive authentication failures are mainly exemplified. A data analysis model is established to obtain a hidden danger assessment coefficient, which is compared with a preset hidden danger threshold to obtain a comparison result. According to different comparison results, the probability of tampering is determined, and an operation strategy for the hidden danger monitoring result is determined based on the similarity of the electrical signals converted from the weights of the same object by the sensor; however, in Embodiment 1, only the identification of tampering is considered, and the remaining hidden dangers are not analyzed or processed. It can be understood that there are some seemingly harmless data encodings (especially data camouflage or hidden encoding), which are interspersed in the data transmission process to confuse the preset digital signature, and then avoid the tampering detection of the system through time delay or replay attack, resulting in the system being unable to detect the tampering risk of the remaining hidden dangers in time and causing delayed identification; for the above problems, Embodiment 2 of the present invention is further refined;

[0092] S4: Obtain the hidden danger monitoring result, detect the hidden danger assessment coefficient corresponding to the hidden danger monitoring result, obtain the identification point corresponding to the hidden danger assessment coefficient, and collect the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point;

[0093] Specifically, the hidden danger monitoring result includes a marker signal;

[0094] Detecting the hidden danger assessment coefficient corresponding to the hidden danger detection result refers to the hidden danger assessment coefficient greater than or equal to the hidden danger threshold in the above Embodiment 1. The identification point corresponding to the specific hidden danger assessment coefficient is also described in the above Embodiment 1 and will not be elaborated here;

[0095] The security of the transmission data signature corresponding to the identification point refers to whether the data packet can ensure the integrity, authenticity, and non-tamperability of the data through the digital signature mechanism during data upload. Its acquisition logic is to determine the signature algorithm type used by the data packet corresponding to each identification point, and through combining the algorithm type and the key length, set a weighted average calculation to obtain the security of the transmission data signature corresponding to the identification point;

[0096] Specifically, the signature algorithms used by the data packets corresponding to each identification point may be different, and the key lengths of the signature algorithms are also different. Substitute the signature algorithm type and the key length of the signature algorithm into the weighted average calculation to obtain the security of the transmission data signature corresponding to the identification point;

[0097] Among them, for the algorithm type, its security score can be determined according to theoretical analysis. The experimenter can set different security scores to divide the security assessment of the algorithm, which will not be elaborated here;

[0098] The calculation efficiency of the transmission data signature corresponding to the recognition point refers to the time and resource consumption required for the system to calculate and generate the signature when uploading data. When the resource consumption and required time increase, redundant data segments or hidden data in the data are mined to determine the importance of potential hazards. Its acquisition logic is to comprehensively calculate and analyze through the signature generation time and signature verification time to obtain the calculation efficiency of the transmission data signature corresponding to the recognition point;

[0099] Specifically, the calculation efficiency of the transmission data signature corresponding to the recognition point is obtained according to the following formula; ;

[0100] In the formula, is the calculation efficiency of the transmission data signature corresponding to the recognition point, is the signature generation time, is the signature verification time;

[0101] S5: Obtain the security of the transmission data signature corresponding to the recognition point and the calculation efficiency of the transmission data signature corresponding to the recognition point, substitute them into the fuzzy logic for fuzzy reasoning, and obtain the result of the potential hazard level;

[0102] For example, "High", "Low", "Medium" for the security of the transmission data signature corresponding to the recognition point, "Fast", "Slow", "Moderate" for the calculation efficiency of the transmission data signature corresponding to the recognition point;

[0103] Formulate a set of fuzzy rules to describe the influence of different input variables on the output variable. The definition of the rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0104] Mark the security of the transmission data signature corresponding to the recognition point as X, the calculation efficiency of the transmission data signature corresponding to the recognition point as U, and the result of the potential hazard level as C_Public;

[0105] Then it can be defined as: Rule 1: IF (X is High) AND (U is Fast) THEN (C_Public is High) Rule 2: IF (U is Low) AND (U is Slow) THEN (C_Public is Low) ...

[0106] Perform fuzzy reasoning according to the fuzzy rules to determine the result of the potential hazard level;

[0107] It should be noted that the division of the fuzzy sets can be adjusted according to the actual situation. For example, although three fuzzy sets are taken as an example in this embodiment, in fact, the security of the transmission data signature corresponding to the recognition point and the calculation efficiency of the transmission data signature corresponding to the recognition point can be divided into more than three sets to facilitate more accurate adjustment according to different signature algorithms.

[0108] Furthermore, for the high, medium, and low judgments of the security of the transmission data signature corresponding to the recognition point and the calculation efficiency of the transmission data signature corresponding to the recognition point, thresholds can be set for judgment according to the actual situation. For example, when the security of the transmission data signature corresponding to the recognition point exceeds 80%, it is labeled as "High", and when the calculation efficiency of the transmission data signature corresponding to the recognition point is higher than 75%, it is labeled as "Fast", etc., which will not be elaborated here;

[0109] The present invention obtains the hidden danger monitoring results, detects the hidden danger evaluation coefficients corresponding to the hidden danger monitoring results, obtains the recognition points corresponding to the hidden danger evaluation coefficients, collects and formulates a set of fuzzy rules for fuzzy inference based on the security of the transmission data signature corresponding to the recognition points and the calculation efficiency of the transmission data signature corresponding to the recognition points, and determines the hidden danger degree results, which can deeper excavate the hidden data and hidden risks of the weighing data of the electronic scale and improve the accuracy of the weighing data.

[0110] Embodiment 3

[0111] Please refer to Figure 2 , a tampering recognition system based on the weighing data of an electronic scale, including a data acquisition module, a data analysis module, a tampering analysis module, and a hidden danger evaluation module;

[0112] The data acquisition module is used to collect the electronic scale feature information and the data integrity feature information, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the upload data packet content, the integrity of the data upload, and the number of consecutive authentication failures, and send them to the data analysis module;

[0113] The data analysis module is used for the time difference between the upload time and the actual weighing time, the difference in the size of the upload data packet content, the integrity of the data upload, and the number of consecutive authentication failures, establish a data analysis model, obtain the hidden danger evaluation coefficient, and send it to the tampering analysis module;

[0114] The tampering analysis module is used to obtain the hidden danger evaluation coefficient, compare it with the preset hidden danger threshold to obtain a comparison result, determine the probability of tampering according to different comparison results, and determine the hidden danger monitoring result according to the similarity of the electrical signals converted by the sensor for the same object, and send it to the hidden danger evaluation module;

[0115] The potential hazard assessment module is used to obtain the results of potential hazard monitoring, detect the potential hazard assessment coefficients corresponding to the potential hazard monitoring results, obtain the identification points corresponding to the potential hazard assessment coefficients, collect the security of the transmission data signature corresponding to the identification points and the calculation efficiency of the transmission data signature corresponding to the identification points, and substitute them into fuzzy logic for fuzzy inference to obtain the results of the potential hazard degree.

[0116] The above formulas are all dimensionless and take their numerical calculations. The formula is a formula obtained by collecting a large amount of data for software simulation to get the closest real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0117] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0118] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0119] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0120] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0121] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0122] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0124] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0125] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. A method for identifying tampering of electronic scale weighing data, characterized in that: include: S1: Collect the characteristic information of the electronic scale and the characteristic information of data integrity, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet, the integrity of the data upload, and the number of consecutive identity authentication failures; S2: Obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet, the completeness of the data upload, and the number of consecutive identity authentication failures, establish a data analysis model, and obtain the hidden danger assessment coefficient; S3: Obtain the hidden danger assessment coefficient and compare it with the preset hidden danger threshold to obtain the comparison result. According to different comparison results, determine the probability of tampering, and determine the hidden danger monitoring result according to the similarity of the electrical signal converted by the sensor from the weight of the same object; S4: Obtain hidden danger monitoring results, detect hidden danger assessment coefficients corresponding to the hidden danger monitoring results, obtain identification points corresponding to the hidden danger assessment coefficients, collect transmission data signature security corresponding to the identification points and transmission data signature calculation efficiency corresponding to the identification points; S5: Obtain the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point, substitute them into fuzzy logic for fuzzy reasoning, and obtain the hidden danger degree result.

2. The method for identifying tampering based on electronic scale weighing data according to claim 1, characterized in that: The characteristic information of the electronic scale includes the time difference between the upload time and the actual weighing time and the difference in the content size of the uploaded data packet; the characteristic information of data integrity includes the completeness of the data upload and the number of consecutive identity authentication failures; By defining the actual weighing time point and the data upload time point, and then subtracting the actual weighing time point from the data upload time point, the time difference between the upload time and the actual weighing time is obtained. ; Where i is the i-th identification point; By defining the actual upload data packet size and the expected upload data packet size, the actual upload data packet size minus the absolute value of the expected upload data packet size is used to obtain the upload data packet content size difference. ; The integrity of data upload is obtained by calculating the number of data fields that are consistent with the checksum of the uploaded data packet, marking it as the number of data fields that are successfully uploaded, and counting the total number of data fields scheduled to be uploaded. The ratio of the number of data fields that are successfully uploaded to the total number of data fields scheduled to be uploaded is calculated. ; By setting the time window first, if the time difference between two failure events recorded in the preset time window is less than the set time window value, it will be recorded as a continuous failure. The system will keep the count of continuous failures until the continuous failure event ends. Based on the count of continuous failures, the number of consecutive identity authentication failures is obtained. .

3. The method for identifying tampering based on electronic scale weighing data according to claim 2, characterized in that: Obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data package, the completeness of the data upload, and the number of consecutive identity authentication failures to establish a data analysis model and generate a hidden danger assessment coefficient , based on the formula: ； In the formula, is the hidden danger assessment coefficient, , , as well as The time difference between the upload time and the actual weighing time , upload data packet content size difference , Completeness of data upload and the number of consecutive authentication failures The preset scaling factor of , , as well as Both are greater than 0.

4. The method for identifying tampering based on electronic scale weighing data according to claim 3, characterized in that: After obtaining the hidden danger assessment coefficient, compare and analyze the hidden danger assessment coefficient with the continuously iterated hidden danger threshold; If the hidden danger assessment coefficient is greater than or equal to the hidden danger threshold, the current electronic scale weighing data is marked as hidden danger data and a risk signal is generated; If the hidden danger assessment coefficient is less than the hidden danger threshold, the current electronic scale weighing data is marked as safe data and a safety signal is generated.

5. The method for identifying tampering based on electronic scale weighing data according to claim 4, characterized in that: Perform multiple calculations to obtain multiple hidden danger assessment coefficients and their comparison results, count the number of times the hidden danger data is marked and the corresponding hidden danger assessment coefficient values, then count the number of all hidden danger assessment coefficients and their corresponding hidden danger assessment coefficient values, and substitute them into the formula to calculate and obtain the probability of tampering; The specific formula is: ； In the formula, is the probability of tampering, n is the total number of potential danger assessment coefficients, q is the number of times data is marked as potential danger data, is the hidden danger assessment coefficient calculated for the first time, is the hidden danger assessment coefficient calculated for the second time, is the hidden danger assessment coefficient calculated for the qth time, is the hidden danger assessment coefficient calculated for the nth time.

6. The method for identifying tampering based on electronic scale weighing data according to claim 5, characterized in that: Prioritize identifying the same object by setting the object number for the object, obtain the corresponding electrical signal, extract the frequency component of the signal as the feature vector through Fourier transform of the electrical signal, and use the cosine similarity calculation to obtain the similarity of the electrical signal converted by the sensor from the weight of the same object; The weighted average calculation is performed on the similarity of the electrical signals converted by the sensor from the weight of the same object and the probability of tampering to obtain the tampering monitoring coefficient, which is then compared with the preset monitoring threshold. If the tampering monitoring coefficient is greater than or equal to the monitoring threshold, it indicates that tampering has occurred and an alarm signal is generated. If the tampering monitoring coefficient is less than the monitoring threshold, it means that some hidden dangers exist and a marking signal is generated; Screen out alarm signals and mark the marking signals as hidden danger monitoring results.

7. The method for identifying tampering based on electronic scale weighing data according to claim 6, characterized in that: By determining the signature algorithm type used for the data packet corresponding to each identification point, and by combining the algorithm type and key length, a weighted average calculation is set to obtain the signature security of the transmission data corresponding to the identification point; Through comprehensive calculation and analysis of signature generation time and signature verification time, the calculation efficiency of the transmission data signature corresponding to the identification point is obtained.

8. The method for identifying tampering based on electronic scale weighing data according to claim 7, characterized in that: The security of the transmission data signature corresponding to the identification point and the computational efficiency of the transmission data signature corresponding to the identification point are defined as input variables, and they are divided into different fuzzy sets respectively; Define the hidden danger degree result as the output variable and divide it into fuzzy sets; Formulate fuzzy rules to describe the impact of the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point on the hidden danger degree results; Perform fuzzy reasoning based on fuzzy rules to determine the degree of hidden dangers.

9. A tampering identification system based on electronic scale weighing data, used to implement a tampering identification method based on electronic scale weighing data as claimed in any one of claims 1 to 8, characterized in that: It includes data collection module, data analysis module, tampering analysis module and hidden danger assessment module; The data acquisition module is used to collect the characteristic information of the electronic scale and the characteristic information of data integrity, and perform normalization processing to obtain the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet content, the integrity of the data upload, and the number of consecutive identity authentication failures, and send them to the data analysis module; The data analysis module is used to establish a data analysis model based on the time difference between the upload time and the actual weighing time, the difference in the size of the uploaded data packet, the integrity of the data upload, and the number of consecutive identity authentication failures, obtain the hidden danger assessment coefficient, and send it to the tampering analysis module; The tampering analysis module is used to obtain the hidden danger assessment coefficient and compare it with the preset hidden danger threshold to obtain the comparison result. According to different comparison results, the probability of tampering is determined, and the hidden danger monitoring result is determined according to the similarity of the electrical signal converted by the sensor from the weight of the same object, and sent to the hidden danger assessment module; The hidden danger assessment module is used to obtain hidden danger monitoring results, detect the hidden danger assessment coefficient corresponding to the hidden danger monitoring results, obtain the identification point corresponding to the hidden danger assessment coefficient, collect the security of the transmission data signature corresponding to the identification point and the calculation efficiency of the transmission data signature corresponding to the identification point, substitute fuzzy logic for fuzzy reasoning, and obtain the hidden danger degree result.

Images