National relationship quantification method fusing decline factor and tampering relationship

Abstract

The invention relates to the fields of artificial intelligence, big data processing and the like, and provides a recession factor and tampering relationship fused national relationship quantification method, which comprises the following steps: constructing a national relationship quantitative analysis index system; calculating a country relationship quantitative value based on the country relationship quantitative analysis index system; and correcting the country relationship quantized value by fusing the decline factor and the talent relationship. According to the method, the decline influence of past events on the national relationship and the influence of other countries on the national relationship are comprehensively considered, more accurate quantitative calculation of the national relationship can be realized, an automatic rapid technology of the national relationship is supported under the clamping of a quantitative rule and a quantitative method, and rapid and accurate quantitative calculation of the national relationship is comprehensively realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the fields of artificial intelligence, big data processing, and the like, in particular to a method for quantifying national relations by fusing recession factors and he-he relations. BACKGROUND

[0002] National relations are the performance of interactions and connections between countries in politics, economy, culture, and military, and are an important basis for understanding international situations. There are two methods, qualitative analysis and quantitative analysis. The qualitative analysis heavily relies on the experience and cognition of analysts, and the results are highly subjective. The quantitative analysis quantifies indicators by designing an index system and quantification rules, and quantifying indicators based on data, and comprehensively obtains the quantitative value of national relations. The quantitative analysis method is scientific, objective, and rigorous, and the results are highly interpretable and reliable, so the analysis of national relations has gradually shifted from qualitative analysis to quantitative analysis.

[0003] The existing method for quantitatively analyzing national relations completely relies on people to establish an index system, design rules, and mine data. In the information age of massive data, it is inefficient and difficult to see all the data to mine national relation indicators from massive data by relying on people. The existing method for quantitatively analyzing national relations does not consider the influence of previous events and other countries on national relations, resulting in inaccurate analysis results. SUMMARY

[0004] The present application aims to provide a method for quantifying national relations by fusing recession factors and he-he relations to solve the problems of low efficiency, lack of automation, and incomplete analysis results in the human-oriented method for quantifying national relations.

[0005] The present application provides a method for quantifying national relations by fusing recession factors and he-he relations, comprising:

[0006] constructing an index system for quantitatively analyzing national relations;

[0007] calculating a quantitative value of national relations based on the index system for quantitatively analyzing national relations;

[0008] fusing recession factors and he-he relations to correct the quantitative value of national relations.

[0009] In some embodiments, the construction of the index system for quantitatively analyzing national relations comprises:

[0010] constructing a framework of the index system for analyzing national relations, comprising a target layer, a criterion layer subordinate to the target layer, and a scheme layer subordinate to the criterion layer; wherein the target layer is the quantification of national relations, the indicators of the criterion layer represent the analysis field, and the indicators of the scheme layer represent the specific dimensions of the analysis;

[0011] The index weight of each index in the national relationship quantitative analysis index system is designed, the trigger threshold and the type are designed, wherein the index weight refers to the contribution of the next layer index to the previous layer index, including the scheme layer index weight and the criterion layer index weight, and the product of the scheme layer index weight and the criterion layer weight is the comprehensive weight of the scheme layer index; the trigger threshold represents the trigger condition of the index affecting the national relationship; the type includes the cost type and the benefit type, the cost type represents that the index has a negative influence on the target, and the benefit type represents that the index has a positive influence on the target.

[0012] In some embodiments, the national relationship quantitative value is calculated based on the national relationship quantitative analysis index system, including:

[0013] Event data and key elements related to each index in the national relationship quantitative analysis index system are obtained; the key elements include a subject country / region, an object country / region, a behavior, a category, and an abstract;

[0014] Based on the event data and the key elements, an index quantification rule is designed;

[0015] The national relationship quantitative value calculated based on the index quantification rule.

[0016] In some embodiments, the index quantification rule is designed based on the event data and the key elements, including:

[0017] Task-oriented data correlation is performed based on the event data and the key elements, and an associated data set is obtained;

[0018] Data and rule-driven index quantification is completed based on the associated data set.

[0019] In some embodiments, the task-oriented data correlation based on the event data and the key elements includes:

[0020] For event data satisfying the association rule 1, a preliminary screening data set of the index is obtained; the association rule 1 is expressed as:

[0021] max(sim(country_sub j ,country_A),sim(country_sub j ,country_B))+sim(country_obj j ,country_else)≥MAX1

[0022] Wherein, max() represents a maximum value function, country_else represents a country country_A and a country country_B, and country_sub jThe countries / regions left after taking max(), sim() represents the similarity calculation function; country_sub j country_obj j country_obj; MAX1 represents the preset threshold of association rule 1;

[0023] For the initial screening data set satisfying the association rule 2, the association data set of the index is obtained; the association rule 2 is expressed as:

[0024]

[0025] Wherein, α is any element in the summary word set div_set t obtained based on the event data in the initial screening data set, and β is any element in the threshold element set the_element_set i corresponding to the index.

[0026] In some embodiments, the association data set is used to complete data and rule driven index quantification, including:

[0027] (1) Cost type index quantification rule, expressed as:

[0028] quantized i = tanh(contribute_value i )

[0029] contribute_value i = -len(rel_data_set i )

[0030] (2) Benefit type index quantification rule, expressed as:

[0031] quantized i = tanh(contribute_value i )

[0032] contribute_value i = len(pos_rel_data_set i )-len(neg_rel_data_set i )

[0033] Wherein, quantized i represents the quantization value of the index index i , and contribute_value i represents the index index iThe contribution value of the state relation, pos_rel_data_set i represents the data with positive sentiment found from the association data set rel_data_set i neg_rel_data_set i represents the data with negative sentiment found from the association data set rel_data_set i len() represents a function of calculating the number of elements in a set, and tanh() represents a hyperbolic tangent function.

[0034] In some embodiments, the state relation quantification value calculated based on the index quantification rule comprises:

[0035]

[0036] wherein A represents a state country_A, B represents a state country_B, r now_event (A, B) represents a state relation quantification value between the state country_A and the state country_B, com_w i represents a comprehensive weight of a scheme layer index in the state relation analysis index system, and I represents the number of the scheme layer indexes in the state relation analysis index system.

[0037] In some embodiments, the fusion decay factor and the inter-state relation correct the state relation quantification value, comprising:

[0038] The fusion decay factor corrects the state relation quantification value to obtain a first corrected value of the state relation;

[0039] The fusion decay factor corrects the first corrected value of the state relation to obtain a second corrected value of the state relation.

[0040] In some embodiments, the fusion decay factor corrects the state relation quantification value, comprising:

[0041]

[0042] wherein r now_event (A, B) represents a state relation between the state country_A and the state country_B in a task period, r past_self_k (A, B) represents a state relation between the state country_A and the state country_B in the kth period without considering the inter-state relation, r now_self (A, B) represents a first corrected value of the state relation, that is, a state relation superimposed with the influence of past events without considering the inter-state relation; K represents an interaction event influence decay period in a past period, and γ kγk is the decay factor of the first K time periods of the task time period k γk is the decay factor of the first K time periods of the task time period

[0043] In some embodiments, the fusion decay factor corrects the country relationship first correction value, comprising:

[0044]

[0045]

[0046] Wherein, A represents country country_A, B represents country country_B, O p represents the other countries involved in the pth he-he relationship; r result (A→B) represents the country relationship second correction value, that is, the final country relationship quantitative value, δ is the weight of the straight link, 1-δ is the total weight of all he-he relationships, w p (1≤p≤T) represents the weight of the intermediate link p in the he-he relationship, con p (1≤p≤k) is the relationship influence degree of the country.

[0047] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present application are:

[0048] The present application comprehensively considers the decay influence of past events on the country relationship and the influence of other countries on the country relationship, can realize more accurate quantitative calculation of the country relationship, and under the support of the quantitative rules and the quantitative method, supports the automatic and rapid technology of the country relationship, and comprehensively realizes the rapid and accurate quantitative calculation of the country relationship. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 A flow chart of a country relationship quantitative method fusing a decay factor and a he-he relationship is provided for the embodiments of the present application

[0050] Figure 2 A frame schematic diagram of a country relationship quantitative analysis index system is provided for the embodiments of the present application.

[0051] Figure 3 A country relationship structure schematic diagram of a he-he relationship is provided for the embodiments of the present application.

[0052] Figure 4 A structure schematic diagram of an electronic device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0053] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0054] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the present application.

[0055] Embodiments

[0056] In order to solve the problems of low efficiency, lack of automation, and incomplete analysis results in the human-oriented national relationship quantitative calculation method, the embodiments of the present application provide a national relationship quantitative method fusing decay factors and he-he relationships. The method uses big data processing technology, combines national relationship analysis index quantitative rules, and realizes national relationship quantitative analysis for massive data. Meanwhile, the decay influence of past events on national relationship and the influence of other countries on national relationship are comprehensively considered.

[0057] As shown in Figure 1 The national relationship quantitative method fusing decay factors and he-he relationships provided by the embodiments of the present application includes the following steps:

[0058] Step 1: Constructing a national relationship quantitative analysis index system. In order to better realize national relationship quantitative analysis, the national relationship quantitative analysis index system is constructed from multiple dimensions and multiple angles through data searching, expert visiting, questionnaire investigation and other forms.

[0059] Step 2: Calculating national relationship quantitative values based on the national relationship quantitative analysis index system. According to the concept connotation of each index in the national relationship quantitative analysis index system, the quantitative rules of national relationship analysis indexes are designed, and the national relationship quantitative values are preliminarily calculated by weighted superposition.

[0060] Step 3: Fusing decay factors and he-he relationships to correct the national relationship quantitative values. The national relationship quantitative values preliminarily obtained in step 2 do not consider the influence of past events and other countries on national relationship, so the national relationship quantitative values in step 2 are inaccurate. Therefore, based on past event decay factors and he-he relationships, the national relationship quantitative values are corrected, so that the national relationship quantitative values are more accurate.

[0061] The following detailed description of the fusion recession factor and the state relationship quantification method of his relationship is described by a specific example.

[0062] Step 1: Construct a state relationship quantification analysis index system.

[0063] The state relationship quantification analysis index system is the result of abstractly describing the variables that affect the state relationship, including the index framework and the index weight and trigger condition.

[0064] Step 1.1: Construct the framework of the state relationship analysis index system.

[0065] From different perspectives, a diversified and multi-dimensional key variable index system can make the evaluation conclusion more stereoscopic and credible. Considering that state relationship is the performance of interaction between countries in politics, economy, culture, military and other aspects, therefore, from the dimensions of military, politics, diplomacy, economy, society and technology, a framework of state relationship analysis index system containing 19 index elements is designed, through the interaction of multiple aspects of the state, the state relationship is fully transparent. As shown in Figure 2 , the framework of the state relationship analysis index system includes:

[0066] The target layer includes: state relationship quantification analysis;

[0067] The criterion layer includes: military, politics, diplomacy, economy, society, and technology;

[0068] The scheme layer includes:

[0069] The military in the criterion layer is refined into military conflict, military deterrence, military aid, and military cooperation;

[0070] The politics in the criterion layer is refined into political visit, political statement, and policy release;

[0071] The diplomacy in the criterion layer is refined into visa policy, diplomatic sanctions, and cultural tourism;

[0072] The economy in the criterion layer is refined into trade investment, economic sanctions, economic policy, and economic aid;

[0073] The society in the criterion layer is refined into historical origin, social cognition, and illegal activity;

[0074] The technology in the criterion layer is refined into technology cooperation and technology sanctions.

[0075] Step 1.2: Design the index weight, trigger threshold and type of each index in the state relationship quantification analysis index system.

[0076] The index weight refers to the contribution of the next layer index to the previous layer index.

[0077] The trigger threshold refers to the effect on the indicator when a certain key element appears in the data or matches the key element, thereby affecting the national relationship.

[0078] Based on the analytic hierarchy process and expert experience, the importance of the indicators in the scheme layer and the criterion layer is judged to obtain a judgment matrix. After weight calculation and consistency check, the contribution degree of the next layer indicator to the previous layer is finally obtained. In this embodiment, the national relationship analysis indicator weight and the trigger threshold are shown in Table 1.

[0079] Table 1, national relationship analysis indicator weight:

[0080]

[0081]

[0082] In Table 1, the criterion layer indicator represents the analysis field; the scheme layer indicator represents the specific dimension of the analysis; the weight represents the contribution degree of the scheme layer indicator to the corresponding criterion layer indicator; the comprehensive weight represents the contribution degree of the scheme layer indicator to the target layer national relationship (the product of the scheme layer indicator weight and the criterion layer indicator weight, wherein the criterion layer indicator weight is the corresponding percentage in Table 1); the trigger threshold represents the triggering condition of the indicator affecting the national relationship; the type represents whether the influence of the scheme layer indicator on the national relationship is positive or negative, wherein the cost type represents that the indicator has a negative influence on the target, and the benefit type represents that the indicator has a positive influence on the target.

[0083] Step 2: Calculate the national relationship quantitative value based on the national relationship quantitative analysis indicator system.

[0084] Through data analysis and processing, based on the indicator trigger threshold, the indicator quantification rule is designed. Finally, based on the data processing result, the national relationship is quantitatively calculated by using the indicator quantification rule.

[0085] Step 2.1: Obtain event data and key elements related to each indicator in the national relationship quantitative analysis indicator system.

[0086] The external representation of the national relationship is the interaction of the national subjects in the fields of military, politics, diplomacy, etc. Therefore, in order to overcome the problems of difficult quantitative analysis and unreliable results caused by data missing, a network crawler tool is used to crawl a large number of news reports from mainstream media, covering multiple fields such as politics, economy, military, and diplomacy.

[0087] The interaction of state relations involves subjects, objects, and behaviors, so the subject state / region, object state / region, and behavior of the news are important. At the same time, different indicators require different data for quantification, so the framework of the state relationship quantification analysis indicator system is used as a standard to design a data classification system, and in order to compress long and valuable text into high-value short text to quickly grasp the information of the full text. In summary, the key elements of event data include subject state / region, object state / region, behavior, category, and abstract.

[0088] At present, pre-training large models represented by ChatGPT learn knowledge representation and general knowledge from massive data, and have strong semantic understanding, natural language processing, reasoning and judgment, and generalization ability. Therefore, in the state relationship quantification evaluation system, a large language model (LLM) is used, and through few-shot learning (FSL), the model obtains the five key elements of subject state / region, object state / region, behavior, category, and abstract from news data.

[0089] Step 2.2: Based on the event data and its key elements, design index quantification rules.

[0090] Data is the basis for index quantification, and quantification rules are the criteria for index quantification. Accurate quantification results require both data and quantification criteria. Therefore, the index quantification process includes task-oriented data association and data rule-driven index quantification.

[0091] Step 2.2.1: Based on event data and its key elements, perform task-oriented data association to obtain associated data sets.

[0092] Suppose the task wants to analyze the relationship between country A and country B. Step 2.1 has classified the collected event data according to the framework of the state relationship analysis indicator system. Then, for any scheme layer indicator index i , the event data set belonging to the indicator index i is obtained, and is denoted as event data set event_set i . According to the trigger threshold requirement of the indicator index i , the data information that can be used to support the indicator index i is associated and found from the event data set event_set i .

[0093] Let event event j = (title j , content j , country_subj ,country_obj j ,act j ,category j ,abstract j ), wherein title j ,content j ,country_sub j ,country_obj j ,act j ,category j ,abstract j respectively represent the title, content, subject country / region, object country / region, action, category, and abstract of the event event j . When event event j ∈event_set i , category j = index i .

[0094] Correlation rule 1: According to the task analysis object, screen the correlation data. If the country relationship between the task analysis country country_A and the country country_B is to be analyzed, if the country_sub j ,country_obj j of event event j satisfy the condition:

[0095] max(sim(country_sub j ,country_A),sim(country_sub j ,country_B))+sim(country_obj j ,country_else)≥MAX1

[0096] wherein max() represents the maximum value function, that is, the maximum value is taken from the two numerical values, MAX1 represents the preset threshold of the correlation rule 1 (which can be set according to the needs, for example, it can be preferably taken as 1.75), country_else represents the country / region remaining in the country country_A and the country country_B after taking max() of country_sub j , and sim() represents a similarity calculation function, denoted as x = (x1, x2, …, x n ), y = (y1, y2, …, y n ), then:

[0097]

[0098] Therefore, to calculate sim(country_sub j , country_B), it is necessary to vectorize country_sub j , country_obj j , country_A and country_B, and use word2vec technology to realize the vectorization coding of the text.

[0099] For the event data set satisfying rule 1, the preliminary screening data set pre_event_set i of index i. is obtained.

[0100] Association rule 2: According to the threshold condition of the index, determine the associated data. For any event t ∈pre_event_set i , the abstract abstract t is segmented by using the jieba segmentation technology, and the abstract segmentation set div_set t is obtained. Denote the set of all threshold elements of index i as the_element_set i , and apply word2vec technology to vectorize the abstract segmentation set div_set t and all elements of the threshold element set the_element_set i . If the abstract segmentation set div_set t of the event event t and the threshold element set the_element_set i of the index index i satisfy the condition:

[0101]

[0102] Where, α is any element in the abstract segmentation set div_set t , β is any element in the threshold element set the_element_set i , and MAX2 represents the preset threshold of the association rule 2 (which can be set according to the needs, for example, it can be preferred to take 0.8). In all data sets satisfying the association rule 2, the associated data set rel_data_set i of index i is obtained.

[0103] Step 2.2.2: Complete data and rule-driven indicator quantification based on the associated dataset.

[0104] Based on whether the indicator has a positive or negative impact on state relations, program-level indicators are categorized as either benefit-based or cost-based. Benefit-based indicators indicate that the occurrence of events associated with the indicator has a positive impact on state relations, while cost-based indicators indicate that the occurrence of events associated with the indicator has a negative impact on the outcome. See Table 1 for a detailed classification. Targeted quantitative rules are designed for different types of indicators.

[0105] (1) Quantification rules for cost-based indicators: Assume that the indicator index i It is a cost-type indicator, and its associated dataset is rel_data_set i . Note this type of index as index i The contribution value to national relations is contribute_value i =-len(rel_data_set i ), where len() is a function that finds the number of elements in a set. However, the range of national relations is [-1, 1], meaning that the quantitative range of each indicator is [-1, 1]. The hyperbolic tangent function tanh() can convert any number continuously to [-1, 1], expressed as:

[0106]

[0107] Apply tanh() to the index i Based on the contribution value of i quantized i =tanh(contribute_value i ).

[0108] (2) Quantification rules for benefit-type indicators: Whether benefit-type indicators have a positive or negative impact on national relations is also positively correlated with the sentiment of the data associated with the national benefit-type indicators. For example, if the data associated with the benefit-type indicator's political stance shows that country_A criticizes country_B, then this political stance has a negative impact on the relationship between country_A and country_B; on the contrary, if country_A politically identifies with country_B, then this has a positive impact on the relationship between country_A and country_B. Therefore, the benefit-type indicator index i and its associated dataset rel_data_set i . Use large language models and few-sample learning techniques to let the model learn from the associated dataset rel_data_set iFind the data with positive sentiment, recorded as pos_rel_data_set i , negative data is recorded as neg_rel_data_set i . Record efficiency index i The contribution value to national relations is contribute_value i =len(pos_rel_data_set i )-len(neg_rel_data_set i ), use tanh() to get the efficiency index i quantized value i =tanh(contribute_value i ).

[0109] Step 2.3: Calculate the quantitative value of national relations based on the indicator quantification rules.

[0110] Through the quantitative rules, the indicators based on the associated data are quantified. Combining the quantitative values ​​of the indicators and the comprehensive weights of the indicators in Table 1, the quantitative value of the national relationship between country_A and country_B based on the event data during the mission time period is obtained. This relationship currently does not consider the influence of the "attenuation factor" and other relationships, and is recorded as r now_event (A,B):

[0111]

[0112] Among them, com_w i It represents the comprehensive weight of the program-level indicators shown in Table 1, and I represents the number of program-level indicators. Under the national relationship analysis indicator system shown in Table 1, I = 19.

[0113] Step 3: fusing the decay factor and other relationships to correct the quantitative value of the national relationship.

[0114] Since past events and interference from other countries will affect the relationship between two countries, in order to quantify state relations more accurately, the "attenuation factor" and other relations are taken into account in the quantitative calculation of state relations.

[0115] Step 3.1: Correct the quantified value of the national relationship by integrating the attenuation factor to obtain a first corrected value of the national relationship.

[0116] The relationship between the two countries is not only affected by the current time interaction events between the two countries, but also by the interaction events in the past time period. For example, the economic sanctions between the two countries will not only affect the current relationship between the two countries, but also cast a shadow on the future relationship between the two countries. Assuming that the interaction event influence decay period in the past time period is K, in order to comprehensively consider the influence of past events on the relationship between countries, the decay factor γ is designed for the first K time periods in the task time period k ∈(0,1),k=1,2,3,.....,K,then the calculation formula of the relationship between countries in the task time period is:

[0117]

[0118] Wherein, r now_event (A,B) represents the relationship between country country_A and country country_B in the task time period, r past_self_k (A,B) represents the relationship between country country_A and country country_B in the kth time period without considering the relationship between the two countries, r now_self (A,B) represents the first corrected value of the relationship between countries, that is, the relationship between countries superimposed with the influence of past events without considering the relationship between the two countries.

[0119] Step 3.2: Fuse the decay factor to correct the first corrected value of the relationship between countries to obtain the second corrected value of the relationship between countries, that is, the final quantitative value of the relationship between countries.

[0120] “Enemies of enemies are friends”, when calculating the relationship between me and him, the relationship between him and him should be considered. Assuming that the task requires to analyze the relationship between country country_A and country country_B, and country country_A and country country_C are in hostile relationship, and country country_B and country country_C are in friendly relationship, it can be deduced that there should be certain hostile relationship between country country_A and country country_B. Therefore, when considering the relationship between country country_A and country country_B, the relationship between country country_A and country country_C, country country_C and country country_B should be considered. Record other countries as country_O1, country_O2, …, country_O T , then the relationship between countries considering the relationship between him and him is shown in Figure 3 .

[0121] Therefore, by Figure 3It can be seen that in calculating the country relationship between country A and country B, in addition to considering the direct relationship between country A and country B, the relationship between country A and country O t and country O t and country B should also be considered, where t = 1, 2,..., T, and T is the number of other countries.

[0122] In calculating the relationship between country A and country B, the direct relationship between country A and country B has the greatest impact, but the international influence of countries is different, which can cause differences in their influence on the relationship between country A and country B. By considering factors such as country area, population, and international influence, countries are divided into three categories: large international influence countries, medium international influence countries, and small international influence countries. The influence of he-he relationships in different influence countries on the relationship between country A and country B is different, and the division rules are shown in Table 2.

[0123] Table 2, country influence level division rules:

[0124]

[0125] Because the straight-line link has the greatest impact on the result, in order to avoid too many he-he relationships weakening the impact of straight-line links, consider setting the weight of straight-line links to a fixed value δ, then the total weight of all he-he relationships is 1-δ. In order to facilitate calculation, set the number of countries involved in he-he relationships to T, then when calculating the comprehensive relationship, T+1 links will be involved.

[0126] Through Table 2, the relationship influence degree of each country is obtained, denoted as con p (1≤p≤k), using the softmax normalization function, the total weight 1-δ is allocated to the T intermediate links, and the weight w p (1≤p≤T) of the intermediate link p is obtained, and the calculation formula is as follows:

[0127]

[0128] Fusing the T he-he relationship involved countries, the quantitative value r result (A→B) of the country relationship between country A and country B is obtained.

[0129]

[0130] Wherein, A represents country country_A, B represents country country_B, O p represents the other country involved in the pth he-she relationship.

[0131] Based on the same technical concept, the embodiments of the present application also provide an electronic device which can implement the method and process of quantifying the country relationship by fusing the recession factor and the he-she relationship provided by the above-mentioned embodiments of the present application. In an embodiment, the electronic device can be a server, a terminal device or other electronic device. As shown in Figure 4 The electronic device can include:

[0132] at least one processor, and a memory connected with the at least one processor, and the specific connection medium between the processor and the memory is not limited in the embodiments of the present application, Figure 4 In the embodiments of the present application, the connection between the processor and the memory is taken as an example by bus connection. The bus is represented by a thick line in Figure 4 the embodiments of the present application, and the connection mode between other components is only schematically illustrated and is not limited. The bus can be divided into address bus, data bus, control bus, etc., for the convenience of representation, Figure 4 only one thick line is used in the embodiments of the present application, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor can also be called a controller, and the name is not limited.

[0133] In the embodiments of the present application, the memory stores instructions executable by the at least one processor, and the at least one processor can execute the foregoing method of quantifying the country relationship by fusing the recession factor and the he-she relationship by executing the instructions stored in the memory. The processor can realize the functions of various modules in the device as shown in Figure 4

[0134] Wherein, the processor is the control center of the device, and can utilize various interfaces and lines to connect each part of the whole control device, and through running or executing the instructions stored in the memory and calling the data stored in the memory, the device can process data and realize various functions, thereby monitoring the whole device.

[0135] In an optional design, the processor can include one or more processing units, and the processor can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor. In some embodiments, the processor and the memory can be realized on the same chip, and in some embodiments, they can also be realized on independent chips respectively.

[0136] ​The processor can be a general purpose processor, such as a CPU, a digital signal processor, an application specific integrated circuit, a field programmable gate array, or other programmable logic device, discrete gate or transistor logic, discrete hardware components, can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general purpose processor can be a microprocessor or any conventional processor, etc. The steps of a method for quantifying the state relationship of a fusion recession factor and other relationships according to the embodiments of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in the processor for execution.

[0137] The memory is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory can include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card type memory, random access memory (RAM), static random access memory (SRAM), programmable read only memory (PROM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. The memory is any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited to this. The memory in the embodiments of the present application can also be a circuit or any other device capable of realizing the storage function, used for storing program instructions and / or data.

[0138] By designing and programming the processor, the code corresponding to the method for quantifying the state relationship of a fusion recession factor and other relationships introduced in the foregoing embodiments can be fixed in the chip, so that the chip can execute the steps of the method of the foregoing embodiments when running. How to design and program the processor is a technology known to those skilled in the art, which will not be described here.

[0139] Based on the same inventive concept, the embodiments of the present application also provide a storage medium storing computer instructions, when the computer instructions run on a computer, the computer executes the foregoing method for quantifying the state relationship of a fusion recession factor and other relationships.

[0140] In some alternative embodiments, the present application also provides various aspects of a method for quantifying the state relationship of a country in relation to the decline factor and the he-she relationship in the form of a program product, which includes program codes for causing the control device to perform the steps of a method for quantifying the state relationship of a country in relation to the decline factor and the he-she relationship according to various exemplary embodiments of the present application described above in the specification when the program product is run on the device.

[0141] It should be noted that although several units or sub-units of the device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units for embodiment. In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all of the illustrated operations must be performed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be split into multiple steps.

[0142] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) having computer-usable program code embodied in the medium.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowcharts and / or block diagrams of the flowcharts and / or block diagrams. Figure 1 The means for carrying out the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams. Figure 1 The means for carrying out the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams.

[0144] Program code to implement the application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. The embodiments are not limited by the

[0145] In the case of using a remote computing device, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by connecting through the Internet using an Internet service provider).

[0146] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a Figure 1 The flow or flows and / or blocks Figure 1 The functions specified in the flow or flows and / or blocks

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow or flows and / or blocks Figure 1 The flow or flows and / or blocks Figure 1 The functions specified in the flow or flows and / or blocks

[0148] The application described and claimed herein is not to be limited in scope by the embodiments described herein since the scope of this application is limited only by the claims. Many modifications and variations of the application described and equivalents thereof will occur to those of ordinary skill in the art upon reading of the foregoing description. The embodiments have been chosen and described in order to best explain the principles of and the information conveyed by the application and the best way to implement the application.

Claims

1. A method for quantifying national relations by integrating decay factors and other relations, characterized in that: include: Constructing a quantitative analysis indicator system for state relations; Calculating the quantitative value of state relations based on the state relations quantitative analysis indicator system; The country relationship quantification value is corrected by integrating the decay factor and other relationships.

2. The method for quantifying national relations by integrating decay factors and other relations according to claim 1, characterized in that: The construction of the quantitative analysis indicator system for state relations includes: The framework for constructing an indicator system for analyzing state relations includes a target layer, a criterion layer below the target layer, and a solution layer below the criterion layer. The target layer is the quantification of state relations, the indicators of the criterion layer represent the analysis areas, and the indicators of the solution layer represent the specific dimensions of the analysis. The indicator weight, trigger threshold and type of each indicator in the quantitative analysis indicator system of state relations are designed; wherein the indicator weight refers to the contribution of the lower-level indicator to the upper-level indicator, including the program-level indicator weight and the criterion-level indicator weight, and the product of the program-level indicator weight and the criterion-level indicator weight is the comprehensive weight of the program-level indicator; the trigger threshold represents the trigger condition for the indicator to affect state relations; the types include cost type and benefit type, the cost type indicates that the indicator has a negative impact on the target, and the benefit type indicates that the indicator has a positive impact on the target.

3. The method for quantifying national relations by integrating decay factors and other relations according to claim 2, characterized in that: The calculating of the quantitative value of national relations based on the national relations quantitative analysis indicator system includes: Obtaining event data and key elements related to each indicator in the national relations quantitative analysis indicator system; the key elements include subject country / region, object country / region, behavior, category, and summary; Design indicator quantification rules based on the event data and its key elements; The quantitative value of national relations is calculated based on the indicator quantification rules.

4. The method for quantifying national relations by integrating decay factors and other relations according to claim 3, characterized in that: The indicator quantification rules are designed based on the event data and its key elements, including: Perform task-oriented data association based on event data and its key elements to obtain associated data sets; Complete data and rule-driven indicator quantification based on associated data sets.

5. The method for quantifying national relations by integrating decay factors and other relations according to claim 4, characterized in that: The task-oriented data association based on event data and its key elements includes: For event data that meets association rule 1, a preliminary screening data set of indicators is obtained; the association rule 1 is expressed as: max(sim(country_sub j ,country_A),sim(country_sub j ,country_B))+sim(coun try_obj j ,country_else)≥MAX1 Among them, max() represents the maximum value function, country_else represents the difference between country_A and country_B and country_sub j The remaining countries / regions after taking max(), sim() represents the similarity calculation function; country_sub j Indicates the country / region of the subject, country_obj j Indicates the object country / region; MAX1 indicates the preset threshold of association rule 1; For the initial screening data set that meets association rule 2, the associated data set of the indicators is obtained; the association rule 2 is expressed as: Among them, α is the summary word set div_set obtained based on the event data in the primary screening dataset t Any element in the_element_set, β is the threshold element set of the corresponding indicator i Any element in .

6. The method for quantifying national relations by integrating decay factors and other relations according to claim 4, characterized in that: The data and rule-driven indicator quantification based on the associated data set includes: (1) Quantification rules for cost-based indicators, expressed as: quantized i =tanh(contribute_value i ) contribute_value i =-len(rel_data_set i ) (2) Quantification rules for benefit-based indicators, expressed as: quantized i =tanh(contribute_value i ) contribute_value i =len(pos_rel_data_set i )-len(neg_rel_data_set i ) Among them, quantized i Indicates index i Quantified value, contribute_value i Indicates index i Contribution value to national relations, pos_rel_data_set i Indicates that the data set rel_data_set i Find the data with positive sentiment, neg_rel_data_set i Indicates that the data set rel_data_set i Find the data with negative sentiment, len() represents the function of finding the number of elements in the set, and tanh() is the hyperbolic tangent function.

7. The method for quantifying national relations by integrating decay factors and other relations according to claim 6, characterized in that: The quantitative value of national relations calculated based on the indicator quantification rule includes: Among them, A represents country_A, B represents country_B, r now_event (A, B) represents the quantitative value of the national relationship between country_A and country_B, com_w i It represents the comprehensive weight of the program-level indicators in the national relationship analysis indicator system, and I represents the number of program-level indicators in the national relationship analysis indicator system.

8. The method for quantifying national relations by integrating decay factors and other relations according to claim 7, characterized in that: The fusion decay factor and other relationships are used to correct the national relationship quantification value, including: Correcting the quantified value of the national relationship by the fusion attenuation factor to obtain a first corrected value of the national relationship; The first correction value of the country relationship is corrected by the fusion attenuation factor to obtain a second correction value of the country relationship.

9. The method for quantifying national relations by integrating decay factors and other relations according to claim 8, characterized in that: The fusion attenuation factor corrects the quantitative value of the national relationship, including: Among them, r now_event (A, B) represents the national relationship between country_A and country_B during the mission time period, r past_self_k (A, B) represents the national relationship between country_A and country_B in the kth period without considering other relationships, r now_self (A, B) represents the first correction value of national relations, that is, the national relations with the influence of past events superimposed without considering other relations; K represents the attenuation period of the influence of interactive events in the past time period, γ k is the attenuation factor for the first K time periods of the task time period, γ k ∈(0,1),k=1,2,3,.....,K。 10. The method for quantifying national relations by integrating decay factors and other relations according to claim 9, characterized in that: The fusion attenuation factor corrects the first correction value of the country relationship, including: Among them, A represents country_A, B represents country_B, p represents the other countries involved in the pth other relationship; r result (A→B) represents the second correction value of the national relationship, that is, the final quantitative value of the national relationship, δ is the weight of the linear link, 1-δ is the total weight of all other relationships, w p (1≤p≤T) represents the weight of the intermediate link p in the other relationship, con p (1≤p≤k) is the relationship influence of the country.

Images