A method for calculating a test result of a criterion question in a psychological test by using bayes theorem, a storage medium, and an electronic device

Abstract

The present application relates to a kind of methods for calculating the results of criterion problem test in psychological test using Bayes theorem, storage medium and electronic equipment, including the subjective priori (lie) probability of being measured person being preset by investigator according to survey result, the acquisition of test atlas original score and the generation of weighted score, the acquisition of atlas probability and the calculation of lie probability.The calculation of lie probability is the core of the present application, and the calculation is by using the recursive formula of Bayes theorem to make all atlas probabilities obtained by test participate in iterative calculation, obtain a final posteriori (lie) probability, and the size of the posteriori (lie) probability and the priori (lie) probability are compared to overturn or affirm the preset probability of investigator, and then determine whether the person being measured lies.Different from prior art, the present application improves communication efficiency, and does not require specific requirements for the number of test stimuli, and fully utilizes the work effort of survey unit on previous survey.

Description

Technical Field

[0001] This invention relates to the field of psychological testing and assessment technology, and in particular to a method, storage medium, and electronic device for calculating the test results of the standard problem in psychological testing using Bayes' theorem. Background Technology

[0002] Initially, the analysis of the plumb line problem test patterns was limited to visual observation and lacked a systematic processing method. Later, Backster in the United States used a scoring method to quantitatively analyze the test patterns, advancing the analysis of the plumb line problem test patterns from qualitative to quantitative analysis by a significant step. As research progressed, researchers began to weight the three physiological channels of respiration, blood pressure, and skin conductance, as well as the weight of the three tests. However, there was no corresponding objective and fixed mature analytical procedure for comprehensively judging a large number of test patterns. Personal subjective experience played a decisive role to some extent, and the processing methods were highly individualistic, making them difficult to promote, apply, and communicate.

[0003] Professor Chen Yunlin discovered in his work that using Bayes' theorem and calculating the advantage ratio can improve the certainty of conclusions in tests of standard problems. The advantage ratio also improves the efficiency of communication with investigators. However, in the process of communicating test results using the advantage ratio with investigators, there were still issues with the investigators' understanding of the advantage ratio. Investigators questioned whether a numerical probability could represent the accuracy of the test. Another problem with advantage ratio calculation is that a certain number of test stimuli are needed to reach the threshold for advantage judgment; if the number of test stimuli is insufficient, the threshold cannot be reached. Finally, the advantage ratio approach completely avoids the investigators' initial investment and does not fully utilize their confidence in a specific case.

[0004] Further information related to the above technical solutions can be found in the following documents:

[0005] Existing technologies, such as the system testing and graph analysis method based on Bayesian theory disclosed in patent number CN110600120A, describe the calculation of the odds ratio as follows: In psychological testing, Bayesian decision-making is achieved through the dominance expression (likelihood ratio L) of Bayes' theorem. The dominance expression of Bayes' theorem not only completely avoids the influence of so-called "prior probability" mathematically, but its greatest contribution is that it can derive joint dominance from joint probabilities, and thus derive evidence weights. Through the integration of various information points, it achieves the advancement and transformation from "uncertainty" to "certainty." Compared to previous accuracy methods, using the changes in prior and posterior probabilities and evaluating them using the odds ratio (L) is easier to understand and master.

[0006] In the process of realizing this invention, the inventors discovered the following problems in the prior art:

[0007] In existing technologies, when reporting test conclusions to survey units, personnel often find the concept of advantage ratios unclear and difficult to understand, leading to questions and even confusion. Using Bayes' theorem to process data requires a certain number of test stimuli to reach the threshold for advantage judgment. Calculating the advantage ratio based on the probability of the test pattern completely avoids prior probability in its calculation method, seemingly making it more objective. However, this effectively negates the significant human, material, and financial resources invested by the survey unit in the preliminary investigation, wasting the advantage of Bayes' theorem in handling subjective probabilities. In short, these technologies suffer from low communication efficiency, require a certain number of test stimuli, and fail to fully utilize the information gathered by the survey unit in the preliminary investigation. Summary of the Invention

[0008] In view of the above problems, this application provides a method, storage medium and electronic device for calculating the test results of the standard problem in psychological testing using Bayes' theorem, in order to solve the technical problems of low communication efficiency, certain requirements on the number of test stimuli and inability to fully utilize the preliminary survey information of the survey unit in the processing technology.

[0009] To achieve the above objectives, in a first aspect, the inventors provide a method for calculating the test results of the criterion problem in psychological testing using Bayes' theorem, comprising:

[0010] Prior probability obtained

[0011] Based on the preliminary investigation results of the investigation unit, a subjective probability of the test subject lying is preset, which is the prior probability of the standard problem test in the psychological test. This prior probability is the starting point for calculating the result of the standard problem test in the psychological test.

[0012] Obtaining raw scores

[0013] In each standard problem test format, the relevant-comparison problem pairs are called scoring points. The test subject's spectral data are assigned scores according to certain rules to obtain the raw score.

[0014] Generation of weighted scores

[0015] By weighting the raw scores, the raw scores of the scoring points can be converted into weighted scores. Multiple tests are conducted on the test subjects, and the final weighted score is obtained by weighting the physiological parameters and the number of test passes.

[0016] Derivation of Spectral Probability

[0017] The probability of each assigned point is calculated using the graph probability formula by weighted scoring.

[0018] Posterior probability calculation

[0019] Using Bayes' theorem, the prior probability, with the added benefit of the first deception graph probability, is transformed into the posterior probability of that deception graph probability. This posterior deception probability then becomes the prior probability of the next deception graph probability. This process is iterated until all deception graph probabilities are included in the calculation and the final deception posterior probability is obtained. Based on the final deception posterior probability, the honesty probability can be calculated. This honesty probability is then used as the prior probability of the first honest graph probability. The above steps are repeated to obtain the final honesty posterior probability. Based on this honesty posterior probability, the final lying probability is obtained.

[0020] Unlike existing technologies, the above technical solution pre-determines a subjective probability of the subject lying based on the preliminary investigation results of the investigation unit personnel. This is the prior probability. Using Bayes' theorem, the prior probability is transformed into the posterior probability of the deception graph by calculation with the support of the deception graph probability. The posterior probability of the deception graph probability is then calculated by adding the deception graph probability. By comparing the magnitude of the posterior probability and the prior probability, the prior probability formed during the investigation process can be affirmed or denied. Thus, iteratively deriving a numerical probability from prior probabilities with the support of spectral probabilities is easier to understand, thereby improving communication efficiency. Furthermore, there are no specific requirements regarding the number of test stimuli. For cases with limited information, traditional advantage ratio calculations often yield inconclusive test results. The method proposed in this application, however, provides a trend of posterior probability changes with the prior probability as the origin. This provides decision-making information to support the investigation unit's next steps, thus better leveraging the advantages of psychological testing technology. The original advantage ratio method calculates the spectral probability using an advantage ratio approach, circumventing prior probabilities in its calculation form. While seemingly more objective, this approach essentially negates the significant human, material, and financial resources invested by the investigation unit in the preliminary investigation. This method, by incorporating prior probabilities into the calculation process, fully utilizes the investigation unit's efforts in the preliminary investigation.

[0021] As one embodiment of the present invention, the specific steps for calculating the posterior probability are as follows: the investigation unit gives the test subject a prior probability of lying based on the results of the previous investigation. Then, with the support of the first deception probability, a posterior probability of the deception probability is obtained after correction calculation. If there are multiple deception probabilities, the posterior probability becomes the prior probability of the next deception probability. Based on this, the posterior probability of the next deception probability is calculated with the support of the next deception probability. This process can be repeated multiple times until all deception probabilities are involved in the calculation. At this point, a posterior probability of the test subject lying can be obtained.

[0022] The probability of the test subject being honest can be calculated from the posterior probability of lying. This probability of honesty is then used as the prior probability. After modification and calculation with the first honesty probability, a posterior probability of that honesty probability is obtained. If there are multiple honesty probabilities, this posterior probability becomes the prior probability of the next honesty probability. Based on this, the posterior probability of the next honesty probability is calculated. This process is repeated until all honesty probabilities are involved in the calculation. At this point, a posterior probability of the test subject being honest can be obtained. The probability of the test subject lying can then be calculated from this posterior probability of honesty.

[0023] This provides decision-making information to support the next steps taken by the investigating unit.

[0024] In one embodiment of the present invention, based on preliminary investigation, the prior probability of the test subject is obtained as P, and P1, P2...P is obtained through the criterion problem test. m The sum of the graph probabilities P for m deceptions m+1 P m+2 ...P m+n Given n honest probability graphs, and based on existing data, the sensitivity A and specificity S of the criterion problem test are known. Additionally, [the following is omitted as the original text is incomplete and cannot be translated]. and Perform a competitive matching of A, S, and P, i.e.

[0025] According to Bayes' theorem and the probability P1 of the first deception graph, we have:

[0026] At this point, put P 1(欺骗\阳性) As the prior probability of P2, we have:

[0027] By iterating in this way, we can obtain P. m The posterior probability P m(欺骗\阳性) At this time, 1-P m(欺骗\阳性) That is, the prior probability of becoming an honest graph, denoted as

[0028] Based on the probability P of the first honest graph. m+1 Then we have:

[0029] At this point, put P m+1(诚实\阴性) As the honesty probability map P m+2 Given the prior probability, we have:

[0030] By iterating in this way, we can obtain P. m+n The posterior probability P m+n(诚实\阴性)Then 1-P m+n(诚实\阴性) This represents the probability that the person being tested is lying. After calculation, the probability of the person being tested lying increases or decreases from P to 1-P. m+n(诚实\阴性) .

[0031] Thus, using the prior probability of the graph probability, the probability of the test subject lying can be calculated to increase or decrease by 1-P from P. m+n(诚实\阴性) This allows prior probabilities to participate in the calculation process, making full use of the efforts made by the surveying units in the preliminary investigation.

[0032] In one embodiment of the present invention, the raw score is obtained according to a seven-point scoring standard. Based on the degree of difference in the intensity of the evaluation object's response at the scoring points, it is divided into 4 levels and 7 values, namely -3, -2, -1, 0, 1, 2, and 3. When the intensity of the response to the related question is greater than that of the response to the comparison question, it is a negative (–) value, and vice versa, it is a positive (+) value. The number obtained by assigning scores to the graph data using the above seven-point scoring standard is called the raw score.

[0033] Thus, by using the correlation-comparison questions in the standard test format, a raw score is obtained, and the value is generally only taken as a positive or negative integer or zero.

[0034] As one embodiment of the present invention, in the analysis of the test spectrum of the plumb line problem, the determination of the reaction intensity will vary depending on the characteristics of different physiological indicators:

[0035] Respiration is measured using respiratory line length, which is the length of the respiratory curve within the effective respiratory response range. See the attached diagram for an illustration. Figure 2 ;

[0036] Skin conductance (SDC) uses peak height or peak area as a measurement index. Peak height is the vertical distance from the inflection point of the SDC spectrum response within the effective response area to the peak of the SDC wave. Peak area is the area enclosed by the line connecting the rising and falling inflection points of the SDC spectrum within the effective response area and the SDC curve itself. See attached diagram. Figure 3 ;

[0037] Blood pressure is measured by the magnitude of the rise or fall from the baseline. The magnitude of the rise or fall is the vertical distance from the inflection point of the blood pressure chart to the peak of the blood pressure wave. See the attached diagram. Figure 4 .

[0038] Therefore, it is particularly important to maintain consistency in intensity units throughout the analysis of the test spectrum. That is, in the analysis of the skin conductance index, if peak height is used, peak height should be used throughout, and if peak area is used, peak area should be used throughout.

[0039] In one embodiment of the present invention, in the step of generating the weighted score, the weighted score is defined as λ and the physiological channel parameter weight is defined as X. i The weight of the number of test iterations is Y. j Let a, b, and c represent the values ​​of the three channels: respiration, blood pressure, and skin conductance, respectively, where X1 + X2 + ... + X i =1, Y1+Y2+……+Y j =1, then we have:

[0040] λ i =Y1(X1 a1+X1 b1+X1 c1)+Y2(X2 a2+X2 b2+X2 c2)+Y3(X3 a3+X3 b3+X3 c3),

[0041] Where X1+X2+X3=1, Y1+Y2+Y3=1;

[0042] Thus, by assigning weights to the original scores, the original scores of the scoring points can be converted into weighted scores λ.

[0043] In one embodiment of the present invention, in the step of obtaining the spectrum probability...

[0044] When λ < 0, P (不通过|欺骗) =50.00–5λ 3 / 6+0.18λ 2 –9.36λ (Ⅰ)

[0045] When λ≥0, P (通过|诚实) =5λ 3 / 6–0.18λ 2 +9.36λ+52.14 (Ⅱ)

[0046] It was also specifically agreed that:

[0047] (1) When λ = 3 points, take P (不通过|欺骗) =99.9%;

[0048] (2) When λ = –3 points, take P. (通过|诚实) =99.9%.

[0049] Thus, by using the two formulas above, multiple spectral probabilities can be obtained.

[0050] To achieve the above objectives, in a second aspect, the inventors provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in any of the preceding claims.

[0051] To achieve the above objectives, in a third aspect, the inventors provide an electronic device including a processor and a storage medium, wherein the storage medium is the storage medium described above;

[0052] The processor is used to execute a computer program stored in the storage medium to implement the steps of the method as described in any of the preceding statements.

[0053] Unlike existing technologies, the technical solution of this application improves the efficiency of communication with the personnel of the investigation unit regarding test results, does not require specific requirements on the number of test stimuli, and makes full use of the work results and efforts of the investigation unit in the preliminary investigation.

[0054] The above description of the invention is merely an overview of the technical solution of this application. In order to enable those skilled in the art to better understand the technical solution of this application and to implement it based on the description and drawings, and to make the above-mentioned objectives and other objectives, features and advantages of this application easier to understand, the following description is provided in conjunction with the specific embodiments and drawings of this application. Attached Figure Description

[0055] The accompanying drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of specific embodiments of this application and other related content, and should not be considered as limitations on this application.

[0056] In the accompanying drawings of the instruction manual:

[0057] Figure 1 This is a logical diagram illustrating a method for calculating the test results of the criterion problem in psychological testing using Bayes' theorem, according to an embodiment of this application.

[0058] Figure 2 This is a schematic diagram of the breathing line length according to one embodiment of this application;

[0059] Figure 3 This is a schematic diagram of the peak height and wave area of ​​the skin electric field according to an embodiment of this application;

[0060] Figure 4 This is a schematic diagram of blood pressure according to one embodiment of this application;

[0061] Figure 5 This is a schematic diagram of the modules of an electronic device according to an embodiment of this application.

[0062] The reference numerals used in the above figures are explained as follows:

[0063] 10. Electronic devices

[0064] 101. Processor

[0065] 102. Storage medium. Detailed Implementation

[0066] To illustrate the possible application scenarios, technical principles, implementable specific solutions, and achievable objectives and effects of this application in detail, the following description, in conjunction with the listed specific embodiments and accompanying drawings, provides a detailed explanation. The embodiments described herein are merely illustrative of the technical solutions of this application and are therefore intended to limit the scope of protection of this application.

[0067] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0068] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0069] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0070] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order between these entities or operations.

[0071] Unless otherwise specified, the use of terms such as “comprising,” “including,” “having,” or other similar expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0072] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceeding" are understood to exclude the stated number; expressions such as "above," "below," and "within" are understood to include the stated number. Furthermore, in the description of the embodiments in this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups" and "multiple times," unless otherwise explicitly specified.

[0073] This embodiment describes a method, storage medium, and electronic device for calculating the results of the standard problem test in psychological testing using Bayes' theorem. This method can be applied to various application scenarios of psychological testing and lie assessment.

[0074] The main challenge is balancing cost-effectiveness. Both tests can detect viral infections in their early stages, but the high cost due to the low viral load at this stage hinders large-scale adoption. To reduce costs, the virus needs to multiply within the body to a sufficient quantity for low-cost detection. Inspired by this, the probability processing of the "standard problem" test format in psychological testing can adopt this approach. Furthermore, by iteratively processing the graphical probability of the standard problem format using Bayes' theorem, a definite probability value can be obtained. This eliminates the need for strict requirements on the number of test stimuli; even a single suitable stimulus can yield a higher or lower probability after processing. This allows for the determination of whether the probability of the test subject lying is increasing or decreasing, further highlighting the value of psychological testing.

[0075] The "Pride Question" test is a general term for a type of psychological testing stimulus arrangement. It not only has a long history and significant influence on the development of psychological testing technology, but it remains a widely used major testing format today. It mainly consists of irrelevant questions (represented by I), relevant questions (represented by R), and control questions (represented by C). The test-taker's response is generally in the form of "yes or no" or "know or not." It utilizes a comparison of the test-taker's physiological response profile to the "Pride Question" and their physiological response profile to the relevant questions to determine whether there are abnormal reactions, and thus infer the relationship between the test-taker and the case. In terms of stimulus presentation and test-taker response format, it resembles true / false questions in various exams; therefore, the prior probability of this test format is 50%. Specifically, for test subjects suspected of lying, their memories include not only information about the case investigation presented in the test stimuli but also information about past misconduct. As a suspected liar, to avoid being exposed, the test subject will focus their attention on the issues related to preparing the deception rather than the control issues. In this case, due to the stakeholder's perception, the related issues are given greater importance, which is reflected in the physiological response intensity induced by the related issues being greater than that induced by the control issues. Conversely, for innocent test subjects, their memories only include information about past misconduct presented in the test stimuli. Their concern is how to avoid making mistakes on issues they believe should not be lying about to avoid being identified as dishonest. Therefore, their attention is focused on the control issues. In this case, based on the stakeholder's perception, the control issues are given more attentional resources than the related issues, which is reflected in the physiological response intensity induced by the control issues being greater than that induced by the related issues. Following the signal detection theory, in the standard test, based on the design concept of the standard problem test, the standard problem and the related problems can act as signal and noise, respectively. For innocent subjects, the standard question stimulus is a signal, while the relevant question stimulus is noise; conversely, for subjects with "problems," the opposite is true. The Control Question Test was originally developed by Reid to address the shortcomings of the relevant-irrelevant test format. After years of development and refinement, the Control Question Test format has become a universal psychological testing format widely used in various fields.

[0076] The evaluation method adopts the mainstream rules in domestic standard problem testing practice for the collection conditions, procedures, main physiological channels and weights, scoring rules for the graphs, and the acquisition of the graph probability for each stimulus point.

[0077] In existing technologies, when reporting test results to survey units, personnel often find the odds ratio unclear and difficult to understand, leading to questions and even confusion. Using Bayes' theorem to process data requires a certain number of test stimuli to reach the threshold for dominance judgment. More importantly, calculating the odds ratio based on the probability of the test pattern completely avoids prior probability in its calculation method, seemingly making it more objective. However, this effectively negates the significant human, material, and financial resources invested by the survey unit in the preliminary investigation, wasting the advantage of Bayes' theorem in handling subjective probabilities. In short, existing methods of calculating the odds ratio suffer from low communication efficiency, require a certain number of test stimuli, and fail to fully utilize the information gathered by the survey unit in the preliminary investigation.

[0078] According to some embodiments of this application, please refer to Figures 1 to 5 This embodiment relates to a method for calculating the test results of the standard problem in psychological testing using Bayes' theorem, including:

[0079] Prior probability obtained

[0080] Based on the preliminary investigation results of the investigation unit, a subjective probability of the test subject lying is preset, which is the prior probability of the standard problem test in psychological testing. This prior probability is the starting point for calculating the standard problem test results of psychological testing.

[0081] Obtaining raw scores

[0082] In each standard problem test format, the relevant-comparison problem pairs are called scoring points. The test subject's spectral data are assigned scores according to certain rules to obtain the raw score.

[0083] According to some embodiments of this application, optionally, in the step of obtaining the original score,

[0084] The raw scores are obtained according to a seven-point scoring system. Based on the difference in the intensity of the responses of the evaluated objects at the scoring points, they are divided into 4 levels and 7 values, namely -3, -2, -1, 0, 1, 2, and 3. When the intensity of the response to the related question is greater than that of the response to the comparison question, it is a negative (–) value, and vice versa, it is a positive (+) value. The numbers obtained by assigning scores to the graph data using the above seven-point scoring system are called the raw scores.

[0085] Thus, by using the correlation-comparison questions in the standard test format, a raw score is obtained, and the value is generally only taken as a positive or negative integer or zero.

[0086] According to some embodiments of this application, optionally, in the analysis of the caliper problem test spectrum, the determination of the reaction intensity may vary depending on the characteristics of different physiological indicators:

[0087] Respiration is measured using respiratory line length, which is the length of the respiratory curve within the effective respiratory response range. See the attached diagram for an illustration. Figure 2 ;

[0088] Skin conductance (SDC) uses peak height or peak area as a measurement index. Peak height is the vertical distance from the inflection point of the SDC spectrum response within the effective response area to the peak of the SDC wave. Peak area is the area enclosed by the line connecting the rising and falling inflection points of the SDC spectrum within the effective response area and the SDC curve itself. See attached diagram. Figure 3 ;

[0089] Blood pressure is measured by the magnitude of the rise or fall from the baseline. The magnitude of the rise or fall is the vertical distance from the inflection point of the blood pressure chart to the peak of the blood pressure wave. See the attached diagram. Figure 4 .

[0090] Therefore, it is particularly important to maintain consistency in intensity units throughout the analysis of the test spectrum. That is, in the analysis of the skin conductance index, if peak height is used, peak height should be used throughout, and if peak area is used, peak area should be used throughout.

[0091] Generation of weighted scores

[0092] By weighting the raw scores, the raw scores of the scoring points can be converted into weighted scores. Multiple tests are conducted on the test subjects, and the final weighted score is obtained by weighting the physiological parameters and the number of test passes.

[0093] According to some embodiments of this application, optionally, in the step of generating the weighted score,

[0094] Define the weighted score as λ and the physiological channel parameter weight as X. i The weight of the number of test iterations is Y. j Let a, b, and c represent the values ​​of the three channels: respiration, blood pressure, and skin conductance, respectively, where X1 + X2 + ... + X i =1, Y1+Y2+……+Y j =1, then we have:

[0095] λ i =Y1(X1 a1+X1 b1+X1 c1)+Y2(X2 a2+X2 b2+X2 c2)+Y3(X3 a3+X3 b3+X3 c3),

[0096] Where X1+X2+X3=1, Y1+Y2+Y3=1.

[0097] Thus, by assigning weights to the original scores, the original scores of the scoring points can be converted into weighted scores λ.

[0098] Derivation of Spectral Probability

[0099] In the step of obtaining the spectral probability, the spectral probability of each assigned point is calculated using the spectral probability formula through weighted scoring, i.e.:

[0100] When λ < 0, P (不通过|欺骗) =50.00–5λ 3 / 6+0.18λ 2 –9.36λ(Ⅰ)

[0101] When λ≥0, P (通过|诚实) =5λ 3 / 6–0.18λ 2 +9.36λ+52.14(Ⅱ)

[0102] It was also specifically agreed that:

[0103] (1) When λ = 3 points, take P (不通过|欺骗) =99.9%;

[0104] (2) When λ = –3 points, take P. (通过|诚实) =99.9%.

[0105] Thus, by using the two formulas above, multiple spectral probabilities can be obtained.

[0106] Derivation of Spectral Probability

[0107] The probability of each assigned point is calculated using the graph probability formula by weighted scoring.

[0108] Posterior probability calculation

[0109] Using Bayes' theorem, the prior probability, with the added benefit of the first deception graph probability, is transformed into the posterior probability of that deception graph probability. This posterior deception probability then becomes the prior probability of the next deception graph probability. This process is iterated until all deception graph probabilities are included in the calculation and the final deception posterior probability is obtained. Based on the final deception posterior probability, the honesty probability can be calculated. This honesty probability is then used as the prior probability of the first honest graph probability. The above steps are repeated to obtain the final honesty posterior probability. Based on this honesty posterior probability, the final lying probability is obtained.

[0110] According to some embodiments of this application, optionally, in the posterior probability calculation step;

[0111] The investigation unit assigns a prior probability of the test subject lying based on the preliminary investigation results. Then, with the support of the first deception probability, a posterior probability of the deception probability is obtained after correction calculation. If there are multiple deception probability probabilities, the posterior probability becomes the prior probability of the next deception probability. Based on this, the posterior probability of the next deception probability is calculated with the support of the next deception probability. This process can be repeated multiple times until all deception probability probabilities are involved in the calculation. At this point, a posterior probability of the test subject lying can be obtained.

[0112] The probability of the test subject being honest can be calculated from the posterior probability of lying. This probability of honesty is then used as the prior probability. After modification and calculation with the first honesty probability, a posterior probability of that honesty probability is obtained. If there are multiple honesty probabilities, this posterior probability becomes the prior probability of the next honesty probability. Based on this, the posterior probability of the next honesty probability is calculated. This process is repeated until all honesty probabilities are involved in the calculation. At this point, a posterior probability of the test subject being honest can be obtained. The probability of the test subject lying can then be calculated from this posterior probability of honesty.

[0113] In this way, prior probabilities can be used to continuously add spectral probability information to finally calculate a posterior probability. All spectral probability information can be used repeatedly. Through iterative calculation, a posterior probability trend with the prior probability as the origin can be obtained, which can provide decision-making information support for the next steps of the surveyed unit.

[0114] According to some embodiments of this application, optionally, based on preliminary investigation, the prior probability of the test subject is obtained as P, and P1, P2...P is obtained through the criterion problem test. m The sum of the graph probabilities P for m deceptions m+1 P m+2 ...P m+n There are n honest probability graphs. Based on existing data, the sensitivity A and specificity S of the criterion problem test are known. Additionally, [the following is missing from the original text]. and Perform a competitive matching of A, S, and P, i.e.

[0115] According to Bayes' theorem and the probability P1 of the first deception graph, we have:

[0116] At this point, put P 1(欺骗\阳性) As the prior probability of P2, we have:

[0117] By iterating in this way, we can obtain P. mThe posterior probability P m(欺骗\阳性) At this time, 1-P m(欺骗\阳性) That is, the prior probability of becoming an honest graph, denoted as

[0118] Based on the probability P of the first honest graph. m+1 Then we have:

[0119] At this point, put P m+1(诚实\阴性) As the honesty probability map P m+2 Given the prior probability, we have:

[0120] By iterating in this way, we can obtain P. m+n The posterior probability P m+n(诚实\阴性) Then 1-P m+n(诚实\阴性) This represents the probability that the person being tested is lying. After calculation, the probability of the person being tested lying increases or decreases from P to 1-P. m+n(诚实\阴性) .

[0121] Thus, using the prior probability of the graph probability, the probability of the test subject lying can be calculated to increase or decrease by 1-P from P. m+n(诚实\阴性) This allows prior probabilities to participate in the calculation process, making full use of the efforts made by the surveying units in the preliminary investigation.

[0122] This embodiment predetermines the subjective probability of a test subject lying based on the preliminary investigation results of the investigation unit personnel. This is the prior probability. Using Bayes' theorem, the prior probability is transformed into the posterior probability of the deception graph by calculation with the support of the deception graph probability. The posterior probability of the deception graph probability is obtained by calculation with the support of the deception graph probability. By comparing the magnitude of the posterior probability and the prior probability, the prior probability formed in the previous investigation process is affirmed or denied. Thus, iteratively deriving a numerical probability from prior probabilities with the support of spectral probabilities is easier to understand, thereby improving communication efficiency. Furthermore, there are no specific requirements regarding the number of test stimuli. For cases with limited information, traditional advantage ratio calculations often yield inconclusive test results. The method proposed in this application, however, provides a trend of posterior probability changes with the prior probability as the origin. This provides decision-making information to support the investigation unit's next steps, thus better leveraging the advantages of psychological testing technology. The original advantage ratio method calculates the spectral probability using an advantage ratio approach, circumventing prior probabilities in its calculation form. While seemingly more objective, this approach essentially negates the significant human, material, and financial resources invested by the investigation unit in the preliminary investigation. This method, by incorporating prior probabilities into the calculation process, fully utilizes the investigation unit's efforts in the preliminary investigation.

[0123] Specific examples are provided:

[0124] Are you called...?

[0125] Regarding the death of an elderly person, are you willing to answer my questions truthfully?

[0126] Do you know the time of death of the elderly person?

[0127] C. Have you ever taken something that doesn't belong to you?

[0128] Do you know where the old man died?

[0129] Are you... years old this year?

[0130] Do you know the cause of death of this elderly person?

[0131] C. Have you ever been involved in a fight?

[0132] Do you know how the elderly die?

[0133] ...

[0134] Are all your answers the truth?

[0135] Where I represents the irrelevant problem, Sr represents the sacrificial relevant problem, R represents the relevant problem, and C represents the control problem.

[0136] After scoring the test graphs and calculating weighted scores, the following results were obtained through probability calculation:

[0137] Do you know the time of death of the elderly person? The graph is a deception graph, and the deception probability P 1(欺骗) =0.7;

[0138] Do you know the location of the old man's death? The graph is an honest graph, and the probability of honesty is P. 1(诚实) =0.65;

[0139] Do you know the cause of the elderly person's death? (This is a graph of honesty, with an honesty probability of P.) 2(诚实) =0.6;

[0140] Do you know the ways an elderly person dies? (This is a deception graph with a probability of P.) 2(欺骗) =0.75.

[0141] The investigation unit believes that the probability of the subject lying is 0.6. Other literature indicates that the sensitivity A (the degree of certainty in identifying bad people) and specificity S (the degree of certainty in identifying good people) of this technology are at least greater than 0.8. In this case, we take its accuracy and specificity as 0.8.

[0142] According to P 1(欺骗) Given that the probability of the survey unit deceiving the subject is P = 0.7 and P = 0.6, then:

[0143]

[0144] With P 1(欺骗\阳性) =0.84 is P 2(欺骗) Given the prior probability, we have:

[0145]

[0146] At this point, the prior probability P of the honesty graph (诚实\阳性) =1-P 2(欺骗\阳性) =1-0.952=0.048.

[0147] Based on the first honesty probability P 1(诚实) =0.65, then:

[0148]

[0149] With P 1(诚实\阴性) =0.141 is P 2(诚实) Given the prior probability, we have:

[0150]

[0151] The probability of this person deceiving is P. 欺骗 =1-P 2(诚实\阴性) =1 - 0.332 = 0.668

[0152] After four test graphs, the ratio of deception to honesty, which was originally considered to be 0.6:0.4 by the survey unit, increased to 0.668:0.332.

[0153] In a second aspect, the present invention also provides a storage medium storing a computer program that, when executed by a processor, implements the method steps of the first aspect of the present invention.

[0154] In the third aspect, please refer to Figure 5 The present invention also provides an electronic device 10, including a processor 101 and a storage medium 102, the storage medium 102 being the storage medium as described in the second aspect; the processor 101 is used to execute a computer program stored in the storage medium 102 to implement the method steps as described in the first aspect.

[0155] Those skilled in the art will understand that the above embodiments can be provided as methods, apparatus, or computer program products. These embodiments may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. All or part of the steps in the methods involved in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium for executing all or part of the steps described in the methods of the above embodiments. The computer device includes, but is not limited to: personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, smart mobile terminals, smart home devices, wearable smart devices, in-vehicle smart devices, etc.; the storage medium includes, but is not limited to: RAM, ROM, magnetic disks, magnetic tapes, optical disks, flash memory, USB flash drives, portable hard drives, memory cards, memory sticks, network server storage, network cloud storage, etc.

[0156] The above embodiments are described with reference to flowchart illustrations and / or block diagrams of the methods, apparatus (systems), and computer program products according to the embodiments. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a computer device to produce a machine, such that the instructions, which execute via the processor of the computer device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0157] These computer program instructions may also be stored in a computer device-readable storage medium that can direct a computer device to operate in a particular manner, such that the instructions stored in the computer device-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer device, causing a series of operational steps to be performed on the computer device to produce a computer-implemented process, thereby providing instructions that execute on the computer device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0159] It should be noted that although the above embodiments have been described herein, this does not limit the scope of patent protection for this invention. Therefore, any changes and modifications made to the embodiments described herein based on the innovative concept of this invention, or equivalent structural or procedural transformations made using the description and drawings of this invention, directly or indirectly applying the above technical solutions to other related technical fields, are all included within the scope of patent protection for this invention.

Claims

1. A method for calculating the test results of the standard problem in psychological testing using Bayes' theorem, characterized in that, include: Prior probability obtained Based on the preliminary investigation results of the investigation unit, a subjective probability of the test subject lying is preset, which is the prior probability of the standard problem test in the psychological test. This prior probability is the starting point for calculating the result of the standard problem test in the psychological test. Obtaining raw scores In each standard problem test format, the relevant-comparison problem pairs are called scoring points. The test subject's spectral data are assigned scores according to certain rules to obtain the raw score. Generation of weighted scores By weighting the raw scores, the raw scores of the scoring points can be converted into weighted scores. Multiple tests are conducted on the test subjects, and the final weighted score is obtained by weighting the physiological parameters and the number of test passes. Derivation of Spectral Probability The probability of each assigned point is calculated using the graph probability formula by weighted scoring. Posterior probability calculation Using Bayes' theorem, the prior probability is transformed into the posterior probability of the first deception graph probability by calculation. This posterior deception probability then becomes the prior probability of the next deception graph probability. This process is repeated iteratively until all deception graph probabilities are included in the calculation and the final deception posterior probability is obtained. Based on the final deception posterior probability, the honesty probability can be calculated. This honesty probability is used as the prior probability of the first honest graph probability. The above steps are repeated to obtain the final honesty posterior probability. Based on this honesty posterior probability, the final lying probability is obtained. The specific steps for calculating the posterior probability are as follows: the investigation unit gives the test subject a prior probability of lying based on the results of the previous investigation. Then, with the support of the first deception probability, a posterior probability of the deception probability is obtained after correction calculation. If there are multiple deception probability probabilities, the posterior probability becomes the prior probability of the next deception probability. Based on this, the posterior probability of the next deception probability is calculated with the support of the next deception probability. This process can be repeated multiple times until all deception probability probabilities are involved in the calculation. At this point, a posterior probability of the test subject lying can be obtained. The probability of the test subject being honest can be calculated from the posterior probability of lying. This probability of honesty is then used as the prior probability. With the addition of the first honesty probability, a posterior probability of that honesty probability is obtained after correction. If there are multiple honesty probabilities, this posterior probability becomes the prior probability of the next honesty probability. Based on this, the posterior probability of the next honesty probability is calculated. This process is repeated until all honesty probabilities are involved in the calculation. At this point, a posterior probability of the test subject being honest can be obtained. The probability of the test subject lying can then be calculated from this posterior probability of honesty. By continuously adding information about the spectral probability to the prior probability, a posterior probability can be calculated. All the spectral probability information can be used repeatedly. Through iterative calculation, a trend of posterior probability change with the prior probability as the origin can be obtained. Based on the preliminary investigation, the prior probability of the test subject was obtained as P. The probability of P1, P2, ..., P was obtained through the criterion problem test. m The sum of the graph probabilities P for m deceptions m+1 P m+2 ... P m+n Given n honest probability graphs, and based on existing data, the sensitivity A and specificity S of the criterion problem test are known. Additionally, [the following is omitted as the original text is incomplete and cannot be translated]. , and Perform competitive matching of A, S, and P, i.e. =1-A, =1-S, =1-P; According to Bayes' theorem and the probability P1 of the first deception graph, we have: At this point, put P 1（欺骗\阳性） As the prior probability of P2, we have: This process is iterated continuously until P is obtained. m The posterior probability P m（欺骗\阳性） At this time, 1-P m（欺骗\阳性） That is, the prior probability of becoming an honest graph, denoted as ; Based on the probability P of the first honest graph. m+1 Then we have: At this point, put P m+1（诚实\阴性） As the honesty probability map P m+2 Given the prior probability, we have: This process is iterated continuously until P is obtained. m+n The posterior probability P m+n(诚实\阴性) Then 1-P m+n(诚实\阴性) This represents the probability that the person being tested is lying. After calculation, the probability of the person being tested lying increases or decreases from P to 1-P. m+n(诚实\阴性) ; Using the prior probability of spectral probability, the probability that the subject is lying is calculated to increase or decrease from P to 1-P. m+n(诚实\阴性) .

2. The method for calculating the test results of the standard problem in psychological testing using Bayes' theorem according to claim 1, characterized in that, The raw scores are obtained according to a seven-point scoring system. Based on the difference in the intensity of the responses of the evaluated objects at the scoring points, they are divided into 4 levels and 7 values, namely -3, -2, -1, 0, 1, 2, and 3. When the intensity of the response to the related question is greater than that of the response to the comparison question, it is a negative (–) value, and vice versa, it is a positive (+) value. The numbers obtained by assigning scores to the graph data using the above seven-point scoring system are called the raw scores.

3. The method for calculating the test results of the standard problem in psychological testing using Bayes' theorem according to claim 2, characterized in that, In the analysis of the caliper problem test spectrum, the determination of the response intensity varies depending on the response characteristics of different physiological indicators: Breathing is measured using the respiratory line length, which is the length of the respiratory curve within the effective respiratory response range. Skin conductance uses peak height or peak area as a measurement index. The peak height of skin conductance is the vertical distance from the inflection point of the skin conductance spectrum response in the effective response area to the peak of the skin conductance wave, while the peak area of ​​skin conductance is the area enclosed by the line connecting the rising and falling inflection points of the skin conductance spectrum in the effective response area and the skin conductance curve. Blood pressure is measured by the magnitude of the rise or fall from the baseline. The magnitude of the rise or fall is the vertical distance from the inflection point of the blood pressure graph to the peak of the blood pressure wave.

4. The method for calculating the test results of the standard problem in psychological testing using Bayes' theorem according to claim 1, characterized in that, In the step of generating the weighted score, the weighted score is defined as λ, and the physiological channel parameter weight is defined as X. i The weight of the number of test iterations is Y. j Let a, b, and c represent the values ​​of the three channels: respiration, blood pressure, and skin conductance, respectively, where X1 + X2 + ... + X i =1, Y1+Y2+……+Y j =1, then we have: λ i = ( + + )+ ( + + )+ ( + + ), where X1+X2+X3=1, Y1+Y2+Y3=1; By assigning weights to the original scores, the original scores of the assigned points can be converted into weighted scores λ.

5. The method for calculating the test results of the standard problem in psychological testing using Bayes' theorem according to claim 4, characterized in that, In the step of obtaining the probability of the map When λ < 0, P (不通过|欺骗) = 50.00–5λ 3 / 6+0.18λ 2 –9.36λ (I) When λ≥0, P (通过|诚实) = 5λ 3 / 6–0.18λ 2 +9.36λ+52.14 (Ⅱ) At the same time, it was agreed that: (1) When λ = 3 points, take P (不通过|欺骗) =99.9%; (2) When λ = –3 points, take P. (通过|诚实) =99.9%.

6. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 5.

7. An electronic device, characterized in that, Includes a processor and a storage medium, wherein the storage medium is the storage medium as described in claim 6; The processor is used to execute a computer program stored in the storage medium to implement the steps of the method as described in any one of claims 1 to 5.

Images