Ffact verification method and device, equipment and storage medium

Abstract

The invention discloses a fact verification method, device and equipment and a storage medium, relates to the technical field of computers, and is applied to a fact verification system constructed based on a large model and a preset multi-agent security system. Determining a to-be-verified hypothesis corresponding to the to-be-processed information by using the obtained information analysis result; performing multi-dimensional zero hypothesis generation based on the large model and the hypothesis to be verified, and determining a target security policy by using the determined multiple zero hypotheses and data resource information; performing evidence collection through a preset multi-agent security system and a plurality of zero hypotheses, and performing security on each zero hypothesis by using an evidence collection result and a target security strategy to obtain a hypothesis security result; and determining a fact verification result corresponding to the to-be-processed information on the basis of the evidence collection result, the hypothesis authenticity result and a preset multi-dimensional hypothesis verification quantization rule. According to the invention, the efficiency, comprehensiveness, reliability and adaptability of fact verification can be effectively realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a fact verification method, device, equipment and storage medium. Background Art

[0002] With the rapid development of information technology, the amount of information faced by human beings is growing exponentially, and the information contains a large number of assumptions, theories or claims that need to be verified by facts.

[0003] However, in the implementation process of traditional verification schemes, on the one hand, most of the steps from hypothesis decomposition to evidence collection to the formation of verification conclusions require manual intervention and rely on manual analysis and professional judgment, which is not only time-consuming and labor-intensive, but also easily affected by cognitive bias and professional limitations; on the other hand, it usually only implements verification for a single dimension, making the verification not comprehensive enough and resulting in low accuracy of the conclusions. In addition, the scheme is difficult to adapt to multi-field applications, resulting in poor adaptability. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a fact verification method, device, equipment and storage medium, which can effectively realize the automation of fact verification, thereby greatly reducing manual dependence and the subjective bias caused by it, and improving the efficiency, systematicity, comprehensiveness, reliability and adaptability of fact verification. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a fact verification method, which is applied to a fact verification system built based on a large model and a preset multi-agent falsification system, including:

[0006] Parsing the received information to be processed based on the large model, and determining the hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result;

[0007] Generate multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determine a target falsification strategy using the determined multiple null hypotheses and data resource information;

[0008] Collecting evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsifying each of the null hypotheses using the evidence collection results and the target falsification strategy to obtain a hypothesis falsification result;

[0009] Based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule, a fact verification result corresponding to the information to be processed is determined.

[0010] Optionally, parsing the received information to be processed based on the large model, and determining a hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result, includes:

[0011] Parsing the received information to be processed based on the large model to obtain an information parsing result;

[0012] A hypothesis extraction operation and a meaningless word removal operation are triggered based on the information parsing result to determine a hypothesis to be verified corresponding to the information to be processed.

[0013] Optionally, after determining the hypothesis to be verified corresponding to the information to be processed by using the obtained information analysis result, the method further includes:

[0014] When it is determined based on the information analysis result that the preset hypothesis splitting condition is met, a plurality of sub-hypotheses to be verified are determined by splitting the hypothesis to be verified, so as to perform multi-dimensional null hypothesis generation based on the large model and each of the sub-hypotheses to be verified.

[0015] Optionally, the generating of multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determining a target falsification strategy using the determined multiple null hypotheses and data resource information, includes:

[0016] Based on the large model and the characteristic information of the hypothesis to be verified, multi-dimensional null hypothesis generation is performed to obtain multiple null hypotheses constituting complementary relationships;

[0017] By analyzing the importance and verification value of each null hypothesis to the hypothesis to be verified, a first weight corresponding to each null hypothesis is determined based on the analysis result;

[0018] A target falsification strategy is determined based on the characteristic information, data resource information and agent resource information of each of the null hypotheses.

[0019] Optionally, the determining the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and a preset multi-dimensional hypothesis verification quantification rule includes:

[0020] By performing source analysis, quality analysis and relevance analysis on each piece of evidence in the evidence collection result, a second weight corresponding to each piece of evidence is determined based on the evidence analysis result;

[0021] Based on the hypothesis falsification results, a falsification degree analysis is performed on each of the null hypotheses to obtain a falsification degree analysis result corresponding to each of the null hypotheses;

[0022] The corresponding multidimensional hypothesis verification score is determined based on the alternative explanation adjustment factor, the first weight corresponding to each of the null hypotheses and the falsification degree analysis result, and the second weight corresponding to each of the evidences.

[0023] Optionally, collecting evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsifying each of the null hypotheses using the evidence collection results and the target falsification strategy, includes:

[0024] The data collection agent in the preset multi-agent falsification system collects evidences for verifying the multiple null hypotheses from the selected multiple data sources to obtain evidence collection results;

[0025] Based on the data collection agent, a data cleaning operation and a format conversion operation are performed on the evidence collection result to obtain the processed evidence collection result;

[0026] Performing correlation analysis on the data analysis agent in the preset multi-agent falsification system and the processed evidence collection results, filtering the processed evidence collection results based on the correlation analysis results to obtain the filtered evidence collection results;

[0027] Each of the null hypotheses is falsified by using the falsification execution agent in the preset multi-agent falsification system, the filtered evidence collection results and the target falsification strategy to obtain a hypothesis falsification result.

[0028] Optionally, after determining the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule, the method further includes:

[0029] Uncertainty analysis, key evidence extraction and verification conclusion generation are performed based on the fact verification results and the evidence collection results to determine a fact verification report corresponding to the information to be processed.

[0030] In a second aspect, the present application provides a fact verification device, which is applied to a fact verification system constructed based on a large model and a preset multi-agent falsification system, including:

[0031] A hypothesis determination module, used to parse the received information to be processed based on the large model, and determine the hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result;

[0032] A falsification strategy determination module, used to generate multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determine a target falsification strategy using the determined multiple null hypotheses and data resource information;

[0033] A falsification result determination module, used to collect evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsify each of the null hypotheses using the evidence collection results and the target falsification strategy to obtain a hypothesis falsification result;

[0034] A verification result determination module is used to determine the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule.

[0035] In a third aspect, the present application provides an electronic device, including:

[0036] Memory, used to store computer programs;

[0037] The processor is used to execute the computer program to implement the steps of the aforementioned fact verification method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which implements the steps of the aforementioned fact verification method when executed by a processor.

[0039] It can be seen that in this application, through the fact verification system constructed based on the large model and the preset multi-agent falsification system, the received information to be processed is first parsed based on the large model, and the hypothesis to be verified corresponding to the information to be processed is determined using the obtained information parsing results; multi-dimensional null hypothesis generation is performed based on the large model and the hypothesis to be verified, and the target falsification strategy is determined using the determined multiple null hypotheses and data resource information; evidence is collected through the preset multi-agent falsification system and the multiple null hypotheses, and each null hypothesis is falsified using the evidence collection results and the target falsification strategy to obtain the hypothesis falsification result; based on the evidence collection results, the hypothesis falsification results and the preset multi-dimensional hypothesis verification quantitative rules, the fact verification result corresponding to the information to be processed is determined. That is to say, in this application, through the fact verification system constructed based on the large model and the preset multi-agent falsification system, the large model is first used to parse the information to be processed to determine the hypothesis to be verified, and then the large model is used to generate multi-dimensional null hypotheses for the hypothesis to be verified, and the corresponding target falsification strategy is determined using the determined multiple null hypotheses. Afterwards, evidence is collected through a preset multi-agent falsification system, and each null hypothesis is falsified using the evidence collection results and the target falsification strategy. Then, the fact verification results are determined using the evidence collection results, the hypothesis falsification results, and the preset multi-dimensional hypothesis verification quantitative rules. In this way, the automation of fact verification can be effectively realized, thereby greatly reducing manual dependence and the subjective bias caused by it, and improving the efficiency, systematicity, comprehensiveness, reliability, and adaptability of fact verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A flow chart of a fact verification method provided for this application;

[0042] Figure 2 A schematic diagram of the structure of a fact verification device provided in this application;

[0043] Figure 3 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In the implementation process of the traditional verification scheme, on the one hand, since most of the steps from hypothesis decomposition to evidence collection to the formation of verification conclusions require manual intervention and rely on manual analysis and professional judgment, this is not only time-consuming and laborious, but also easily affected by cognitive bias and professional limitations; on the other hand, it usually only implements verification for a single dimension, making the verification not comprehensive enough and resulting in low accuracy of the conclusion. In addition, the scheme is difficult to adapt to multi-field applications, resulting in poor adaptability. To this end, the present application provides a fact verification scheme that can effectively realize the automation of fact verification, thereby greatly reducing manual dependence and the subjective bias caused by it, and improving the efficiency, systematicity, comprehensiveness, reliability and adaptability of fact verification.

[0046] See also Figure 1 As shown, an embodiment of the present invention discloses a fact verification method, which is applied to a fact verification system constructed based on a large model and a preset multi-agent falsification system, including:

[0047] Step S11: parsing the received information to be processed based on the large model, and using the obtained information parsing result to determine the hypothesis to be verified corresponding to the information to be processed.

[0048] In this embodiment, in addition to the large model and the preset multi-agent falsification system, the fact verification system also includes a hypothesis understanding engine, a falsification strategy planner, and an evidence accumulation scoring system. Among them, the hypothesis understanding engine is responsible for receiving and parsing the hypothesis expressed in natural language, extracting the statement or hypothesis to be verified; the falsification strategy planner automatically generates multi-dimensional null hypotheses according to the hypothesis characteristics and designs corresponding verification methods; the multi-agent falsification execution system, that is, the preset multi-agent falsification system is composed of data collection agents, data analysis agents, and falsification implementation agents, and cooperates to perform falsification tasks; the evidence accumulation scoring system is responsible for calculating and updating the verification progress, generating the final multi-dimensional hypothesis verification score (Multi-dimensionalHypothesis Verification Score, MHVS) and report.

[0049] It should be understood that, regarding the information to be processed expressed in natural language, in this embodiment, the hypothesis understanding engine is first used for processing. The hypothesis understanding engine is implemented based on a large language model. Specifically, the large language model is used to extract the information to be processed input into the system by using instructions, and irrelevant modal particles and other information are removed. In addition, if multiple problems are involved, they are divided into multiple sub-problems to facilitate the subsequent generation of null hypotheses. That is, the received information to be processed is parsed based on the large model to obtain the information parsing result; based on the information parsing result, the hypothesis extraction operation and the meaningless vocabulary removal operation are triggered to determine the hypothesis to be verified corresponding to the information to be processed. When it is determined based on the information parsing result that the preset hypothesis splitting condition is met, multiple sub-hypotheses to be verified are determined by splitting the hypothesis to be verified, so as to generate multi-dimensional null hypotheses based on the large model and each of the sub-hypotheses to be verified.

[0050] Step S12: Generate multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determine a target falsification strategy using the determined multiple null hypotheses and data resource information.

[0051] In this embodiment, after the hypothesis to be verified is obtained, the falsification strategy planner will be used to perform relevant processing. The falsification strategy planner is implemented based on a large model, and is responsible for automatically generating multidimensional null hypotheses based on the hypothesis characteristics based on Popper's falsification principle, and designing corresponding verification methods and execution paths. In this way, the authenticity of the main hypothesis can be verified by systematically negating the null hypothesis. Specifically, this embodiment first generates multidimensional null hypotheses based on the large model and the characteristic information of the hypothesis to be verified to obtain multiple null hypotheses that constitute a complementary relationship; by analyzing the importance and verification value of each null hypothesis to the hypothesis to be verified, the first weight corresponding to each null hypothesis is determined based on the analysis results; the target falsification strategy is determined based on the characteristic information, data resource information and intelligent agent resource information of each null hypothesis. In other words, the specific application steps of the falsification strategy planner are as follows:

[0052] (1) Null hypothesis generation: Based on the main hypothesis, i.e., the structured representation of the hypothesis to be verified, multiple complementary null hypotheses are automatically generated to ensure that all key aspects of the main hypothesis are covered. For example, for the main hypothesis of "factor A leads to result B", null hypotheses such as "A and B have no statistical correlation", "the temporal relationship between A and B does not conform to causal logic", and "the relationship between A and B disappears after controlling other variables" can be generated;

[0053] (2) Dimension weight allocation: Assign a corresponding weight (1-10) to each null hypothesis based on its importance and verification value to the main hypothesis;

[0054] (3) Falsification path planning: Based on the characteristics of the null hypothesis and the available data resources and agent resources, plan the optimal falsification execution path, including data requirements and analysis methods. Data requirements include whether online search is required and the scope of online search. Analysis methods include whether external knowledge needs to be referenced.

[0055] The above steps are all implemented using a large model. Through custom instructions, the hypothesis to be verified is input into the large model, and the large model can output one or more corresponding null hypotheses, null hypothesis weights and path planning at one time.

[0056] Step S13: collect evidence through the preset multi-agent falsification system and the multiple null hypotheses, and use the evidence collection results and the target falsification strategy to falsify each null hypothesis to obtain a hypothesis falsification result.

[0057] In this embodiment, after obtaining the null hypothesis and the corresponding target falsification strategy, the preset multi-agent falsification system will be used for corresponding processing. The preset multi-agent falsification system consists of a data collection agent, a data analysis agent, and a falsification implementation agent. These agents work together to execute the verification plan designed by the falsification strategy planner. Specifically, in this embodiment, the data collection agent in the preset multi-agent falsification system first collects evidence to verify the multiple null hypotheses from the selected multiple data sources to obtain evidence collection results; based on the data collection agent, the evidence collection results are subjected to data cleaning operations and format conversion operations to obtain the processed evidence collection results; the data analysis agent in the preset multi-agent falsification system and the processed evidence collection results are subjected to correlation analysis to filter the processed evidence collection results based on the correlation analysis results to obtain the filtered evidence collection results; each null hypothesis is falsified by the falsification execution agent in the preset multi-agent falsification system, the filtered evidence collection results, and the target falsification strategy to obtain the hypothesis falsification results.

[0058] It should be understood that, regarding the agents in the preset multi-agent falsification system, the data collection agent is used to obtain the data required for verification from various data sources (such as academic literature libraries, public databases, network resources, etc.), that is, the collection of evidence. And the agent has the ability to access multi-source data, can perform data cleaning and format conversion, and unify the data into JSON (JavaScript Object Notation) format. In addition, the data collection agent can be divided into multiple professional sub-agents according to needs, such as literature retrieval agents, web crawler agents, database query agents, etc. Through different sub-agents, customized processing can be performed according to each different data source type, including using different interface calling methods, search statement construction methods, result return structures, etc., which can retrieve and obtain data more intelligently. The data analysis agent receives the data provided by the data collection agent, analyzes whether it is related to the proposition, and filters out irrelevant information; because the results of network retrieval may be mixed with a large amount of invalid information such as advertisements, irrelevant information will interfere with the operation of the subsequent evidence accumulation and scoring system, and the data analysis agent can ensure the relevance of the data. The falsification implementation agent follows the path planned by the falsification strategy planner, uses the data selected by the data analysis agent as supplementary information, attempts to falsify each sub-null hypothesis in parallel, lists key evidence in paragraphs, and gives guiding conclusions. In addition, the falsification system also requires an agent coordination mechanism to design communication protocols and collaboration mechanisms between agents, ensure seamless transmission of data and results, and improve overall execution efficiency.

[0059] Step S14: determining a fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and a preset multi-dimensional hypothesis verification quantification rule.

[0060] In this embodiment, after the falsification is completed, the evidence accumulation scoring system will be used for relevant processing. The scoring system is responsible for integrating the hypothesis falsification results of the preset multi-agent falsification system, calculating and updating the verification progress, and finally generating a multidimensional hypothesis verification score (MHVS). The scoring system adopts a scientific scoring formula and interpretation standard, which can realize the quantitative expression and uncertainty measurement of the verification conclusion. Specifically, in this embodiment, the source analysis, quality analysis and correlation analysis of each piece of evidence in the evidence collection result are first performed to determine the second weight corresponding to each piece of evidence based on the evidence analysis result; based on the hypothesis falsification result, the degree of falsification of each null hypothesis is analyzed to obtain the degree of falsification analysis results corresponding to each null hypothesis; based on the alternative explanation adjustment factor, the first weight corresponding to each null hypothesis and the degree of falsification analysis result, the second weight corresponding to each piece of evidence is determined. The relevant steps for scoring are as follows:

[0061] (1) Calculation of evidence weight (i.e., second weight): Assign a weight to each piece of evidence based on factors such as its source, quality, and relevance;

[0062] (2) Evaluation of the degree of falsification of the null hypothesis: Based on the accumulated evidence, evaluate the degree to which each null hypothesis is falsified (0-1);

[0063] (3) Multidimensional hypothesis validation score (MHVS) calculation: The comprehensive score is calculated using the following formula:

[0064] ;

[0065] In the formula, Wi represents the weight of the i-th null hypothesis (1-10); Fi represents the degree of falsification of the i-th null hypothesis (0-1); Ri represents the reliability coefficient of the i-th evidence (0.5-1); C represents the consistency multiplier (0.8-1.2), which is used to evaluate the consistency between evidence; A represents the alternative explanation adjustment factor (0.7-1), which is used to reflect possible alternative explanations. Among them, Wi is the value defined by the falsification strategy planner, and the rest are the values ​​assigned after analysis by the evidence accumulation scoring system.

[0066] (4) Conclusion interpretation criteria:

[0067] The higher the MHVS score, the more likely it is to falsify the null hypothesis, and the more likely it is to prove the original main hypothesis to be true. MHVS > 0.8: The main hypothesis is "highly likely" to be true; 0.6 < MHVS ≤ 0.8: The main hypothesis is "very likely" to be true; 0.4 < MHVS ≤ 0.6: There is insufficient evidence to judge; 0.2 < MHVS ≤ 0.4: The main hypothesis is "very likely" to be false; MHVS ≤ 0.2: The main hypothesis is "highly likely" to be false.

[0068] (5)Report generation: Based on the factual verification results obtained from the analysis, generate a structured verification report, including conclusions, key evidence, the basis for scoring each score, uncertainty analysis, and follow-up suggestions. That is, based on the factual verification results and the evidence collection results, perform uncertainty analysis, extract key evidence, and generate verification conclusions to determine the factual verification report corresponding to the information to be processed.

[0069] In summary, the factual verification system provided in this embodiment has the following technical effects:

[0070] 1) Achieved a high degree of automation in the entire process of hypothesis verification, significantly reducing manual intervention and subjective bias, and improving verification efficiency and consistency;

[0071] 2) Through multi-dimensional null hypotheses and multi-path falsification strategies, improved the systematicness and comprehensiveness of verification, and enhanced the reliability of conclusions;

[0072] 3) Adopted a multi-agent collaboration mode to achieve distributed parallel processing, significantly improving verification efficiency and resource utilization;

[0073] 4) Through the evidence accumulation scoring system, achieved a quantitative expression of verification conclusions and uncertainty measurement, providing a more scientific basis for decision-making;

[0074] 5) Provided efficient and objective factual verification for the content generated by large models, reducing the risk of misinformation dissemination.

[0075] It should be understood that the factual verification system provided in this embodiment can be widely applied to multiple fields such as scientific research, business decision-making, legal evidence analysis, media statement verification, historical event analysis, and artificial intelligence content evaluation.

[0076] It can be seen that in this application, the fact verification system constructed based on the large model and the preset multi-agent falsification system first uses the large model to parse the information to be processed to determine the hypothesis to be verified, and then uses the large model to generate multi-dimensional null hypotheses for the hypothesis to be verified, and uses the determined multiple null hypotheses to determine the corresponding target falsification strategy. Afterwards, evidence is collected by the preset multi-agent falsification system, and each of the null hypotheses is falsified using the evidence collection results and the target falsification strategy. Then the fact verification results are determined using the evidence collection results, the hypothesis falsification results, and the preset multi-dimensional hypothesis verification quantitative rules. In this way, the automation of fact verification can be effectively realized, thereby greatly reducing manual dependence and the subjective bias caused by it, and improving the efficiency, systematicity, comprehensiveness, reliability and adaptability of fact verification.

[0077] The technical solution of the embodiment of the present application is described in detail below in conjunction with actual verification application examples in specific fields.

[0078] In order to fully demonstrate the practicality and effectiveness of the fact verification system of the present invention, two specific application examples are provided below, in which the data are only for illustrative purposes.

[0079] Among them, in the first application example, the fact verification method in the present application can be applied to the fact verification of relevant information in the medical field, that is, the information to be processed in the fact verification method of the present application can be medical information to be processed, and the corresponding large model can be a medical large model. The intelligent agents in the preset multi-agent falsification system can be used to collect and analyze medical-related data.

[0080] Example 1: Scientific hypothesis verification - "Gene BRCA1 mutation increases the risk of breast cancer."

[0081] Input stage: The fact verification system receives the information to be processed: "Gene BRCA1 mutation increases the risk of breast cancer."

[0082] Hypothesis understanding stage: The hypothesis understanding engine parses the hypothesis and extracts the core proposition: There is a causal relationship between mutations in the BRCA1 gene and an increased risk of breast cancer.

[0083] Strategy planning phase: Generate the following null hypothesis based on the falsification strategy planner:

[0084] 1) Null hypothesis 1: There is no statistical correlation between BRCA1 mutation and breast cancer incidence (weight: 9);

[0085] 2) Null hypothesis 2: The association between BRCA1 mutation and breast cancer risk can be fully explained by other factors (weight: 7);

[0086] 3) Null hypothesis 3: The temporal relationship between BRCA1 mutation and breast cancer does not conform to causal logic (weight: 6);

[0087] 4) Plan a falsification path for each null hypothesis, including obtaining data from medical literature libraries, clinical research databases, and online searches for credible sources.

[0088] Parallel execution of the falsification phase: the data collection agent obtains relevant data from the clinical trial database, medical literature library, and authoritative media; the data analysis agent filters the data and retains data such as research results, clinical data, and analytical articles with high relevance; the falsification implementation agent analyzes the data and attempts to falsify each null hypothesis:

[0089] 1) Analysis of Null Hypothesis 1: Several large cohort studies have shown that the risk of breast cancer in BRCA1 mutation carriers is 5-7 times that of the general population, with a p value of <0.0001;

[0090] 2) Analysis of Null Hypothesis 2: After controlling for age, race, lifestyle and other variables, the correlation between BRCA1 mutation and breast cancer risk is still significant;

[0091] 3) Analysis of Null Hypothesis 3: Longitudinal studies show that BRCA1 mutation precedes breast cancer and follows a reasonable biological mechanism.

[0092] Final result synthesis stage:

[0093] 1) Calculate the degree of falsification of each null hypothesis: Null hypothesis 1: F1=0.95 (highly falsified); Null hypothesis 2: F2=0.85 (strongly falsified); Null hypothesis 3: F3=0.90 (strongly falsified).

[0094] 2) Data reliability assessment: R1=0.95 (high reliability); R2=0.85 (relatively high reliability); R3=0.80 (relatively high reliability).

[0095] 3) Analyze and determine the consistency multiplier C=1.1;

[0096] 4) Analyze and determine the alternative explanation adjustment factor A=0.95 (there are other environmental factors);

[0097] 5) Calculate MHVS: (9×0.95×0.95+7×0.85×0.85+6×0.90×0.80) / (9+7+6)×1.1×0.95=0.86.

[0098] Output stage: Generate a verification report with the conclusion that "the main hypothesis is highly likely to be true (MHVS=0.86)". The final report may include a summary of key evidence, the falsification of each null hypothesis and the basis for the weight, and point out that the conclusion may differ between different ethnic groups.

[0099] Among them, in the second application example, the fact verification method in the present application can be applied to the fact verification of relevant information in the automobile field, that is, the information to be processed in the fact verification method of the present application can be the automobile-related information to be processed, and the corresponding large model can be the automobile industry large model. The intelligent agents in the preset multi-agent falsification system can be used to collect and analyze automobile-related data.

[0100] Example 2: Media statement verification - "New energy vehicles are more environmentally friendly than traditional fuel vehicles."

[0101] Input stage: The fact verification system receives the information to be processed: "New energy vehicles are more environmentally friendly than traditional fuel vehicles."

[0102] Hypothesis understanding stage: The hypothesis understanding engine analyzes the hypothesis and determines that the environmental protection comparison to be verified involves the environmental impact of the entire life cycle, rather than just the use phase. The rewritten hypothesis is: New energy vehicles are more environmentally friendly than traditional fuel vehicles in the entire life cycle.

[0103] Strategy Planning Phase: Falsification The strategy planner generates the following null hypothesis:

[0104] 1) Null hypothesis 1: The carbon emissions of new energy vehicles over their entire life cycle are no less than those of traditional fuel vehicles (weight: 8);

[0105] 2) Null hypothesis 2: The environmental burden of the new energy vehicle manufacturing process offsets the environmental advantages of the use phase (weight: 7);

[0106] 3) Null hypothesis 3: After considering the source of electricity, the operating emissions of new energy vehicles are no better than those of traditional fuel vehicles (weight: 6);

[0107] 4) Null hypothesis 4: The environmental damage caused by the disposal of new energy vehicle batteries is greater than that of traditional fuel vehicles (weight: 5);

[0108] 5) Plan a falsification path, including retrieving environmental science research data, industry report data, and searching authoritative sources online.

[0109] The falsification phase is executed in parallel: the data collection agent obtains data from scientific journals, environmental protection agency reports, and industry white papers; the data analysis agent filters and extracts scientifically representative research results, identifies and removes biased data released by stakeholders; the falsification implementation agent analyzes each null hypothesis:

[0110] 1) Analysis of Null Hypothesis 1: A number of authoritative life cycle assessments show that new energy vehicles reduce carbon emissions by 30-60% on average, but there are regional differences;

[0111] 2) Analysis of Null Hypothesis 2: Although the energy consumption of new energy vehicles is higher during the manufacturing stage, the total energy consumption over the entire life cycle is still lower than that of fuel vehicles;

[0112] 3) Analysis of Null Hypothesis 3: Even in areas where coal-based power grids are dominant, the overall carbon emissions of electric vehicles are still slightly lower than or equal to those of high-efficiency fuel vehicles;

[0113] 4) Analysis of Null Hypothesis 4: Battery recycling technology has made significant progress, but there are indeed environmental concerns in the mining and recycling of battery materials.

[0114] Final result synthesis stage:

[0115] 1) Calculate the degree of falsification of each null hypothesis: Null hypothesis 1: F1=0.75 (strong falsification); Null hypothesis 2: F2=0.70 (moderate falsification); Null hypothesis 3: F3=0.60 (moderate falsification); Null hypothesis 4: F4=0.40 (weak falsification);

[0116] 2) Data reliability assessment: R1=0.85 (high reliability); R2=0.80 (high reliability); R3=0.75 (medium reliability); R4=0.70 (medium reliability);

[0117] 3) Analyze and determine the consistency multiplier C=0.9 (there is some controversy);

[0118] 4) Analyze and determine the alternative explanation adjustment factor A=0.85 (there are other environmental factors);

[0119] 5) Calculate MHVS: (8×0.75×0.85+7×0.70×0.80+6×0.60×0.75+5×0.40×0.70) / (8+7+6+5)×0.9×0.85=0.52.

[0120] Output stage: Generate a verification report with the conclusion that “there is insufficient evidence to make a clear judgment (MHVS=0.52)”.

[0121] See also Figure 2 As shown, the embodiment of the present application also discloses a fact verification device, which is applied to a fact verification system constructed based on a large model and a preset multi-agent falsification system, including:

[0122] A hypothesis determination module 11 is used to parse the received information to be processed based on the large model, and determine the hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result;

[0123] A falsification strategy determination module 12, for generating multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determining a target falsification strategy using the determined multiple null hypotheses and data resource information;

[0124] A falsification result determination module 13 is used to collect evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsify each of the null hypotheses using the evidence collection results and the target falsification strategy to obtain a hypothesis falsification result;

[0125] The verification result determination module 14 is used to determine the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule.

[0126] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0127] It can be seen that in this application, the fact verification system constructed based on the large model and the preset multi-agent falsification system first uses the large model to parse the information to be processed to determine the hypothesis to be verified, and then uses the large model to generate multi-dimensional null hypotheses for the hypothesis to be verified, and uses the determined multiple null hypotheses to determine the corresponding target falsification strategy. Afterwards, evidence is collected by the preset multi-agent falsification system, and each of the null hypotheses is falsified using the evidence collection results and the target falsification strategy. Then the fact verification results are determined using the evidence collection results, the hypothesis falsification results, and the preset multi-dimensional hypothesis verification quantitative rules. In this way, the automation of fact verification can be effectively realized, thereby greatly reducing manual dependence and the subjective bias caused by it, and improving the efficiency, systematicity, comprehensiveness, reliability and adaptability of fact verification.

[0128] In some specific embodiments, the hypothesis determination module 11 can be specifically used to: parse the received information to be processed based on the large model to obtain an information parsing result; trigger a hypothesis extraction operation and a meaningless word removal operation based on the information parsing result to determine the hypothesis to be verified corresponding to the information to be processed.

[0129] In some specific embodiments, the fact verification device can also be used to: when it is determined based on the information analysis result that a preset hypothesis splitting condition is met, multiple sub-hypotheses to be verified are determined by splitting the hypothesis to be verified, so as to generate multi-dimensional null hypotheses based on the large model and each of the sub-hypotheses to be verified.

[0130] In some specific embodiments, the falsification strategy determination module 12 can be specifically used to: generate multi-dimensional null hypotheses based on the large model and the characteristic information of the hypothesis to be verified to obtain multiple null hypotheses that constitute a complementary relationship; determine the first weight corresponding to each null hypothesis based on the analysis result by analyzing the importance and verification value of each null hypothesis to the hypothesis to be verified; determine the target falsification strategy based on the characteristic information, data resource information and intelligent agent resource information of each null hypothesis.

[0131] In some specific embodiments, the verification result determination module 14 can be specifically used to: determine the second weight corresponding to each piece of evidence based on the evidence analysis result by performing source analysis, quality analysis and correlation analysis on each piece of evidence in the evidence collection result; perform a falsification degree analysis on each null hypothesis based on the hypothesis falsification result to obtain a falsification degree analysis result corresponding to each null hypothesis; determine the corresponding multidimensional hypothesis verification score based on the alternative explanation adjustment factor, the first weight corresponding to each null hypothesis and the falsification degree analysis result, and the second weight corresponding to each piece of evidence.

[0132] In some specific embodiments, the falsification result determination module 13 can be specifically used to: collect evidence to verify the multiple null hypotheses from the selected multiple data sources through the data collection agent in the preset multi-agent falsification system to obtain evidence collection results; perform data cleaning operations and format conversion operations on the evidence collection results based on the data collection agent to obtain the processed evidence collection results; perform correlation analysis through the data analysis agent in the preset multi-agent falsification system and the processed evidence collection results to filter the processed evidence collection results based on the correlation analysis results to obtain the filtered evidence collection results; falsify each null hypothesis through the falsification execution agent in the preset multi-agent falsification system, the filtered evidence collection results and the target falsification strategy to obtain a hypothesis falsification result.

[0133] In some specific embodiments, the fact verification device can also be used to: perform uncertainty analysis, extract key evidence, and generate verification conclusions based on the fact verification results and the evidence collection results to determine a fact verification report corresponding to the information to be processed.

[0134] Furthermore, the present application also discloses an electronic device. Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0135] Figure 3 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the fact verification method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0136] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0137] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0138] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the fact verification method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0139] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed fact verification method. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, and no further description will be given here.

[0140] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0141] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0143] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0144] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A fact verification method, characterized in that: Applied to fact verification systems built on large models and preset multi-agent falsification systems, including: Parsing the received information to be processed based on the large model, and determining the hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result; Generate multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determine a target falsification strategy using the determined multiple null hypotheses and data resource information; Collecting evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsifying each of the null hypotheses using the evidence collection results and the target falsification strategy to obtain a hypothesis falsification result; Based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule, a fact verification result corresponding to the information to be processed is determined.

2. The fact verification method according to claim 1, characterized in that: The step of parsing the received information to be processed based on the large model, and determining a hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result, includes: Parsing the received information to be processed based on the large model to obtain an information parsing result; A hypothesis extraction operation and a meaningless word removal operation are triggered based on the information parsing result to determine a hypothesis to be verified corresponding to the information to be processed.

3. The fact verification method according to claim 1, characterized in that: After determining the hypothesis to be verified corresponding to the information to be processed by using the obtained information analysis result, the method further includes: When it is determined based on the information analysis result that the preset hypothesis splitting condition is met, a plurality of sub-hypotheses to be verified are determined by splitting the hypothesis to be verified, so as to perform multi-dimensional null hypothesis generation based on the large model and each of the sub-hypotheses to be verified.

4. The fact verification method according to claim 1, characterized in that: The generating of multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determining a target falsification strategy using the determined multiple null hypotheses and data resource information, includes: Based on the large model and the characteristic information of the hypothesis to be verified, multi-dimensional null hypothesis generation is performed to obtain multiple null hypotheses constituting complementary relationships; By analyzing the importance and verification value of each null hypothesis to the hypothesis to be verified, a first weight corresponding to each null hypothesis is determined based on the analysis result; A target falsification strategy is determined based on the characteristic information, data resource information and agent resource information of each of the null hypotheses.

5. The fact verification method according to claim 4, characterized in that: The determining of the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule includes: By performing source analysis, quality analysis and relevance analysis on each piece of evidence in the evidence collection result, a second weight corresponding to each piece of evidence is determined based on the evidence analysis result; Based on the hypothesis falsification results, a falsification degree analysis is performed on each of the null hypotheses to obtain a falsification degree analysis result corresponding to each of the null hypotheses; The corresponding multidimensional hypothesis verification score is determined based on the alternative explanation adjustment factor, the first weight corresponding to each of the null hypotheses and the falsification degree analysis result, and the second weight corresponding to each of the evidences.

6. The fact verification method according to any one of claims 1 to 5, characterized in that: The collecting evidence by using the preset multi-agent falsification system and the multiple null hypotheses, and falsifying each null hypothesis by using the evidence collection results and the target falsification strategy, includes: The data collection agent in the preset multi-agent falsification system collects evidences for verifying the multiple null hypotheses from the selected multiple data sources to obtain evidence collection results; Based on the data collection agent, a data cleaning operation and a format conversion operation are performed on the evidence collection result to obtain the processed evidence collection result; Performing correlation analysis on the data analysis agent in the preset multi-agent falsification system and the processed evidence collection results, filtering the processed evidence collection results based on the correlation analysis results to obtain the filtered evidence collection results; Each of the null hypotheses is falsified by using the falsification execution agent in the preset multi-agent falsification system, the filtered evidence collection results and the target falsification strategy to obtain a hypothesis falsification result.

7. The fact verification method according to claim 1, characterized in that: After determining the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule, the method further includes: Uncertainty analysis, key evidence extraction and verification conclusion generation are performed based on the fact verification results and the evidence collection results to determine a fact verification report corresponding to the information to be processed.

8. A fact verification device, characterized in that: Applied to fact verification systems built on large models and preset multi-agent falsification systems, including: A hypothesis determination module, used to parse the received information to be processed based on the large model, and determine the hypothesis to be verified corresponding to the information to be processed using the obtained information parsing result; A falsification strategy determination module, used to generate multi-dimensional null hypotheses based on the large model and the hypothesis to be verified, and determine a target falsification strategy using the determined multiple null hypotheses and data resource information; A falsification result determination module, used to collect evidence through the preset multi-agent falsification system and the multiple null hypotheses, and falsify each of the null hypotheses using the evidence collection results and the target falsification strategy to obtain a hypothesis falsification result; A verification result determination module is used to determine the fact verification result corresponding to the information to be processed based on the evidence collection result, the hypothesis falsification result and the preset multi-dimensional hypothesis verification quantification rule.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the fact verification method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the fact verification method as claimed in any one of claims 1 to 7.

Images