Method and related device for predicting survival probability

Abstract

The present application provides a method for predicting survival probability and related equipment. The method includes: using a Cox process with random intensity to establish a first predicted survival probability model; adding an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model; combining an exponential jump function to establish a Feller function of a first parameter of the second predicted survival probability model; according to the exponential distribution expectation, setting the second parameter and the third parameter of the second predicted survival probability model to meet a first limiting condition; according to the boundary conditions of the second parameter and the third parameter, combined with the first limiting condition, calculating the second parameter and the third parameter; combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model to calculate a predicted survival probability model; using the predicted survival probability model to predict the survival probability of an individual who is currently x years old after t years.

Description

Technical Field

[0001] The present application relates to the technical field of risk prediction, and in particular to a method for predicting survival probability and related equipment. Background Art

[0002] Since its commercial deployment, 5G has received extensive attention. The application of 5G to empower industries is an important research direction for the current and future mobile Internet, which promotes the development of various vertical industries and aims to provide more real-time and reliable connections for any type of equipment in any application scenario, so as to achieve the goal of supporting and leading the further networking and intelligence of society. 6G will fully support the digitization of the entire world on the basis of 5G, and combine the development of technologies such as big data and artificial intelligence to achieve the ubiquitous availability of wisdom and fully empower everything, promote society to move towards a "digital twin" world that combines virtuality and reality, and realize the beautiful vision of "digital twin, ubiquitous wisdom" in the communication network. Based on this overall vision, the 6G network will give rise to new application scenarios in the three aspects of smart life, smart production, and smart society, such as twin digital people, holographic interaction, super-energy transportation, synaesthesia, and intelligent perception interaction.

[0003] An important extension direction of large-scale machine communication under 5G in the 6G era is the development from machine-to-machine communication to machine-to-human communication, and then to personalized human-to-machine communication. People-centered services (HCS) based on the perception-communication integrated network deserve further study. The development direction of people-centered services in the big health scenario has gradually changed from studying the application of wearable devices and implantable devices on patients to focusing on the prediction of patients' or normal human vital signs, such as potential diseases and natural life span, and then applied to new scenarios such as smart elderly care. Data twins credible situations at a quantifiable level. More accurate characterization of the uncertainty of the probability of natural death of an individual can achieve a mutually credible mapping from reality to virtuality and from actual to estimation, and more accurately enable the perception-communication integration technology to empower personal life.

[0004] However, existing methods and related equipment for predicting survival probability can only roughly measure the survival probability, and cannot accurately describe the randomness of individual death, nor can they describe the differences and uncertainties of individual death risks. Summary of the invention

[0005] In view of this, the purpose of this application is to propose a method for predicting the probability of survival and related equipment. Based on the above purpose, this application provides a method for predicting the probability of survival, characterized in that it includes:

[0006] The first prediction survival probability model was established using the Cox process with random intensity;

[0007] Adding an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model;

[0008] In combination with the exponential jump function, a Feller function is established regarding the first parameter of the second prediction survival probability model;

[0009] According to the exponential distribution expectation, setting the second parameter and the third parameter of the second prediction survival probability model to meet the first limiting condition;

[0010] The second parameter and the third parameter are calculated according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition;

[0011] The predicted survival probability model is calculated by combining the second parameter, the third parameter, the Ferrer function and the second predicted survival probability model; the predicted survival probability model is used to predict the survival probability of an individual who is currently x years old t years later.

[0012] In a possible implementation, the first prediction survival probability model is specifically:

[0013]

[0014] Among them, S x (t) represents the survival probability of an individual of age x after t years, T x represents the future life span of an individual aged x, represents t=0, λ s Represents the non-negative mortality intensity function at time s.

[0015] In a possible implementation, the affine diffusion process satisfies the following formula:

[0016] dX t =μ(X t ,t)dt+σ(X t ,t)dB t

[0017] Among them, X t represents the affine diffusion process, μ(·) represents the affine diffusion structure, σ(·) represents the affine diffusion structure, B t represents Brownian motion.

[0018] In a possible implementation, the Feller function is specifically:

[0019]

[0020] Among them, λ x (t) represents the first parameter, a represents a constant, ε represents a volatility parameter, W trepresents the mortality intensity function with volatility, and J(t) represents the exponential jump function.

[0021] In a possible implementation manner, the first limiting condition is specifically:

[0022]

[0023] Among them, α′(t) represents the differential of the second parameter, β′(t) represents the differential of the third parameter, β(t) represents the third parameter, l represents the jump intensity, a represents a constant, μ represents the affine diffusion structure, and σ represents the affine diffusion structure.

[0024] In a possible implementation, the boundary conditions of the second parameter and the third parameter include:

[0025] When the variable is 0, the second parameter and the third parameter are both 0.

[0026] In a possible implementation, the second parameter and the third parameter are:

[0027]

[0028] Wherein, α(t) represents the second parameter, β(t) represents the third parameter, l represents the jump intensity, μ represents the affine diffusion structure, and a, b, c, and d are all constants.

[0029] Based on the same inventive concept, the embodiment of the present application also provides a device for establishing a prediction uncertainty event model, including:

[0030] a building module configured to build a first predictive survival probability model using a Cox process with random intensity;

[0031] an affine diffusion module, configured to add an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model;

[0032] A building module configured to build a Feller function on a first parameter of a second prediction survival probability model in combination with an exponential jump function;

[0033] A setting module is configured to set the second parameter and the third parameter of the second predicted survival probability model to meet the first limiting condition according to the exponential distribution expectation;

[0034] A calculation module, configured to calculate the second parameter and the third parameter according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition;

[0035] The calculation module is configured to calculate a predicted survival probability model by combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model; and use the predicted survival probability model to predict the survival probability of an individual who is currently x years old t years later.

[0036] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the program, a method for predicting the probability of survival as described in any one of the above is implemented.

[0037] Based on the same inventive concept, an embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, characterized in that the computer instructions are used to enable a computer to execute any one of the methods for predicting survival probability described above.

[0038] From the above, it can be seen that the method and related equipment for predicting survival probability provided by the present application establish a first predicted survival probability model by using a Cox process with random intensity; add an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model; combine the exponential jump function to establish a Feller function about the first parameter of the second predicted survival probability model; according to the exponential distribution expectation, set the second parameter and the third parameter of the second predicted survival probability model to meet the first limiting condition; calculate the second parameter and the third parameter according to the boundary conditions of the second parameter and the third parameter, combined with the first limiting condition; calculate the predicted survival probability model by combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model; use the predicted survival probability model to predict the survival probability of an individual who is now x years old after t years. For the uncertain problem of survival probability, which has randomness, the predicted survival probability model is explicitly expressed by establishing it, thereby improving the robustness and accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of a method for predicting survival probability according to an embodiment of the present application;

[0041] Figure 2This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old female born in 1922 in an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old male born in 1922 in an embodiment of the present application;

[0043] Figure 4 This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old female born in 1932 in an embodiment of the present application;

[0044] Figure 5 This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old male born in 1932 in an embodiment of the present application;

[0045] Figure 6 This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old female born in 1942 in an embodiment of the present application;

[0046] Figure 7 This is a schematic diagram comparing the predicted survival probability and the actual survival probability of a 65-year-old male born in 1942 in an embodiment of the present application;

[0047] Figure 8 A schematic diagram of the structure of a device for predicting the probability of survival according to an embodiment of the present application;

[0048] Fig. 9 This is an electronic device structure for predicting survival probability according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0050] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] As described in the background technology section, the technical solution for predicting survival probability in the related art is to characterize the individual survival probability through constant intensity, which can only roughly measure the survival probability and does not have the individual randomness, resulting in a large deviation between the actual numerical value and the precise value obtained by the mathematical model.

[0052] Therefore, the present application proposes a method for predicting survival probability, which adds randomness to the existing model for predicting survival probability, and further adds different jump parts, so that the predicted survival probability model has randomness compared with the existing technology, thereby achieving the technical effect of describing the uncertainty of individual survival probability through the model.

[0053] The technical solutions of the embodiments of the present application are described in detail below through specific examples.

[0054] refer to Figure 1 The method for predicting the survival probability of the embodiment of the present application comprises the following steps:

[0055] Step S101, establishing a first prediction survival probability model using the Cox process with random intensity.

[0056] In one possible implementation, the survival function is an important benchmark model for measuring the risk of individual death. It refers to the probability that an individual of age x will survive within t years and is expressed as follows:

[0057]

[0058] Among them, S x (t) represents the probability that an individual of age x survives for t years, T x represents the life span of an individual, represents the life span of an individual x The distribution function of t p x It represents the probability that an individual of age x is still alive t years later.

[0059] The present embodiment analyzes the survival function from the perspective of natural mortality, which is defined as the negative derivative of the logarithm of the survival function, and is expressed by the following formula:

[0060]

[0061] Among them, μ x (t) represents the death force, S x (t) represents the probability that an individual of age x survives t years.

[0062] From the above, we can know that the survival function of an individual aged x in t years is transformed into the following formula:

[0063]

[0064] Among them, S x (t) represents the probability that an individual of age x survives for t years, t p x represents the probability that an individual is still alive t years later when his age is x, μ x (t) represents the death force.

[0065] The mortality rate without considering the disease is determined by the current age x and the natural year of birth of the individual. If the natural years are the same, the larger the x, the higher the natural mortality rate. When x is kept constant, due to external factors such as the development of medicine and the improvement of quality of life, the natural mortality rate will decrease slightly with the passage of natural years of birth, and the average life expectancy will be longer at the overall level. Therefore, when modeling and analyzing the survival function of an individual aged x, it is necessary to keep the birth year fixed.

[0066] In the prior art, the natural mortality rate is calculated by roughly observing the survival function using the "Human Mortality Database HMD". HMD is provided by the Max Planck Institute for Demographic Research and the University of California, Berkeley. The database updates the death toll of 38 countries and regions every week. This application selects a 1×1 table, that is, an age interval × year interval table, which records the natural death of individuals of different birth years and different ages. Individuals are estimated a death probability at each age and each natural year, that is, q x , x can take a maximum value of 110. For example, if you want to calculate the probability that a person born in 1922 and now aged x will still be alive t years later, multiply the survival probabilities of each year. The selected individual age is x, and the corresponding natural year of birth is y. If the death probability of x+1 is used, the corresponding natural year is y+1, and so on. The following formula is used to roughly measure the mortality force:

[0067] t p x =(1-q x )(1-q x+1 )....(1-q x+t-1 )

[0068] in, t p x represents the probability that an individual is still alive t years later when his age is x, q x It represents the estimated probability of death of an individual in a natural year when the individual is age x.

[0069] However, the roughly measured mortality rate cannot describe the differences and uncertainties in individual mortality risks. In order to describe the uncertainty, this application introduces a risk regression model, referred to as the Cox process.

[0070] For a non-negative intensity function λ tThe non-homogeneous Poisson process N satisfies the following formula:

[0071]

[0072] Among them, N t Indicates the first jump time, N s represents the initial time, and the time interval k is independent of represents the volatility parameter at a certain point in time, τ represents the current time, s represents the value of the time range considered, and λ u Represents the non-negative mortality intensity function at time u.

[0073] Assume that the first jump time N of the Cox process is t Expressed as τ, the process can be regarded as a Poisson process of uneven intensity, satisfying the following formula:

[0074]

[0075] Where τ represents the first jump time of the Cox process, λ s represents the non-negative mortality intensity function at time s, and E[·] represents the expectation.

[0076] The properties of the Poisson process used in the embodiments of the present application are as follows: A "martingale" is a random process without a drift term.

[0077] The martingale satisfies the following theorem:

[0078] If N t is a Poisson process with a fixed rate λ, then the process N t -λ t is a martingale.

[0079] If N t is the time-varying intensity λ t If the process is non-homogeneous Poisson, then its compensated composite Poisson process is is a martingale.

[0080] The embodiment of the present application regards the survival function of individual patients as a Poisson process of death, and the natural death time is the first jump time of the Poisson process. In the prediction model and Cox process of the embodiment of the present application, the random intensity is allowed to be over-dispersed or fluctuate.

[0081] In a possible implementation, a first prediction survival probability model is established using a Cox process with random intensity, wherein the first prediction survival probability model is specifically:

[0082]

[0083] Among them, Sx (t) represents the survival probability of an individual of age x after t years, T x represents the future life span of an individual aged x, represents t=0, λ s Represents the non-negative mortality intensity function at time s.

[0084] Step S102, adding an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model.

[0085] In one possible implementation, one needs to specify an affine diffusion process as a model of mortality intensity.

[0086] For the affine diffusion process X t ,have

[0087] Among them, G t It indicates that the expectation changes with time t. α(Tt) and β(Tt) need to satisfy the "generalized Riccati ordinary differential equation", which depends on the SDE coefficient of the affine diffusion process. The expressions of α and β can be obtained through the affine diffusion process to solve the survival function model.

[0088] Based on the theorem: If u(x,T) satisfies the following partial differential equation under the restriction condition u(x,T)=1:

[0089]

[0090] Finding the expectation of u, we get the following formula:

[0091]

[0092] And satisfy dX t =μ(X t ,t)dt+σ(X t ,t)dB t , where B t represents Brownian motion.

[0093] Assumptions And the affine diffusion process satisfies the following formula:

[0094] dX t =μ(X t ,t)dt+σ(X t ,t)dB t

[0095] According to the Feynman-Katz formula, if u(X t ,t) conforms to the partial differential equation, then the following equation is satisfied:

[0096]

[0097] At the same time, another conclusion can be drawn: only when μ(X t ,t) and σ 2 (X t ,t) satisfies μ(X t ,t)=a+bX t And σ 2 (X t ,t)=c+rX t When u(X t ,t) can be written as e α(T-t)+β(T-t)X(t) , then the variables satisfy the generalized ordinary differential equation, which in this case is expressed as follows:

[0098]

[0099] Among them, a, b, c, and r are all constants.

[0100] In this patent, this structure of μ and σ is called "affine diffusion structure". This "affine diffusion structure" is applied in the survival function and subsequent models to obtain the Riccati ordinary differential equation, with the focus on explicitly expressing the expressions of α and β in each process, and then solving the model.

[0101] In the embodiment of the present application, the non-negative death force strength λ x (t) is used as an affine diffusion structure. Let T = t and t = 0, then the first predicted survival probability model is converted into the second predicted survival probability model, specifically:

[0102]

[0103] Among them, α(·) represents the parameter, β(·) represents the parameter, S x (t) represents the survival probability of an individual of age x after t years, λ x (·) indicates the intensity of the death force.

[0104] Step S103: establishing a Feller function for the first parameter of the second predicted survival probability model in combination with the exponential jump function.

[0105] Under the concept of the mean reversion model, individual differences will result in the natural mortality rate of only those who are considered to be healthier in old age being in line with objective facts, and it cannot describe the corresponding law of individual natural mortality rate over any time. Since the risk of individual natural death increases over time, the mortality force does not satisfy the mean reversion law, and a non-mean reversion process is needed to characterize the individual's natural mortality rate, and its deterministic trend is exponentially increasing.

[0106] In a possible implementation, the Feller function is specifically:

[0107]

[0108] Among them, λ x (t) represents the first parameter, a represents a constant, ε represents a volatility parameter, W t represents the mortality intensity function with volatility, and J(t) represents the exponential jump function.

[0109] The exponential jump function is calculated by the following formula:

[0110]

[0111] Among them, J t represents the exponential jump function, N t Indicates independence from B t and a standard Poisson process with strength υ, γ k (k=1,2,…,N t ) represents independent and identically distributed random variables.

[0112] Step S104: according to the exponential distribution expectation, setting the second parameter and the third parameter of the second predicted survival probability model to meet the first limiting condition.

[0113] The exponential distribution expectation is specifically:

[0114]

[0115] Among them, β(t) represents the third parameter, γ k (k=1,2,…,N t ) represents independent and identically distributed random variables, η represents γ k The mean value of

[0116] The embodiment of the present application selects a Feller function with a non-mean-reverting process as a basic random process for studying the intensity of natural death, and proposes adding different types of jump parts to the Feller function. According to the Feller function, the generalized Riccati ordinary differential equation is converted into the first limiting condition, and the first limiting condition is specifically:

[0117]

[0118] Among them, α′(t) represents the differential of the second parameter, β′(t) represents the differential of the third parameter, β(t) represents the third parameter, l represents the jump intensity, a represents a constant, μ represents the affine diffusion structure, and σ represents the affine diffusion structure.

[0119] Step S105, calculating the second parameter and the third parameter according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition.

[0120] In a possible implementation, the boundary conditions of the second parameter and the third parameter include:

[0121] When the variable is 0, the second parameter and the third parameter are both 0.

[0122] In a possible implementation, the second parameter and the third parameter are:

[0123]

[0124] Wherein, α(t) represents the second parameter, β(t) represents the third parameter, l represents the jump intensity, μ represents the affine diffusion structure, a, b, c, d are all constants,

[0125] Step S106, calculating a predicted survival probability model by combining the second parameter, the third parameter, the Ferrer function and the second predicted survival probability model.

[0126] In this step, the second parameter, the third parameter and the Feller function related to the first parameter can be known through the above calculation. The second parameter, the third parameter and the Feller function related to the first parameter are introduced into the second predicted survival probability model to calculate the predicted survival probability model.

[0127] Step S107, using the predicted survival probability model to predict the survival probability of an individual who is currently x years old in t years.

[0128] In this embodiment, the male and female data of the HMD UK population database are used to predict the survival probability.

[0129] Prediction results reference Figure 2-Figure 7 , Figure 2-Figure 7 The FELj_1 models in the figure are all predicted survival probability models of the present application, the solid line is the actual survival probability numerical curve, and the dotted line is the survival probability numerical curve predicted by the predicted survival probability model.

[0130] Figure 2-Figure 7 The figure below is a comparison of the predicted and actual survival probabilities for men and women in 1922, 1932, and 1942.

[0131] As can be seen from the figure, the numerical curve of the predicted survival probability is highly consistent with the numerical curve of the actual survival probability, which proves that the values ​​predicted by the predicted survival probability model of the present application are very close to the actual values ​​and have very excellent technical effects.

[0132] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0133] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for predicting the probability of survival.

[0135] refer to Figure 8 , the device for predicting the survival probability comprises:

[0136] Establishing module 21, configured to establish a first prediction survival probability model using a Cox process with random intensity;

[0137] An affine diffusion module 22 is configured to add an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model;

[0138] An establishing module 21 is configured to establish a Feller function of a first parameter of a second prediction survival probability model in combination with an exponential jump function;

[0139] A setting module 23 is configured to set the second parameter and the third parameter of the second predicted survival probability model to meet the first limiting condition according to the exponential distribution expectation;

[0140] A calculation module 24 is configured to calculate the second parameter and the third parameter according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition;

[0141] The calculation module 24 is configured to calculate a predicted survival probability model by combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model; and use the predicted survival probability model to predict the survival probability of an individual who is currently x years old t years later.

[0142] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0143] The device of the above embodiment is used to implement the corresponding method for predicting the survival probability in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0144] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting the survival probability described in any of the above embodiments is implemented.

[0145] Fig. 9 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0146] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0147] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0148] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0149] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0150] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0151] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0152] The electronic device of the above embodiment is used to implement the corresponding method for predicting the survival probability in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0153] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for predicting the survival probability as described in any of the above embodiments.

[0154] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0155] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for predicting the survival probability as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0156] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0157] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0158] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0159] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for predicting survival probability, characterized in that: include: The first prediction survival probability model was established using the Cox process with random intensity; Adding an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model; In combination with the exponential jump function, a Feller function is established regarding the first parameter of the second prediction survival probability model; According to the exponential distribution expectation, setting the second parameter and the third parameter of the second prediction survival probability model to meet the first limiting condition; The second parameter and the third parameter are calculated according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition; Calculating a predicted survival probability model by combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model; using the predicted survival probability model to predict the survival probability of an individual currently aged x years old t years later; The first prediction survival probability model is specifically: in, represents the survival probability of an individual aged x after t years, represents the future life span of an individual aged x, express , Indicates the time Non-negative mortality intensity function when ; The affine diffusion process satisfies the following formula: in, represents the affine diffusion process, represents the affine diffusion structure, represents the affine diffusion structure, represents Brownian motion; The Feller function is specifically: in, represents the first parameter, represents a constant, represents the volatility parameter, represents the mortality intensity function with volatility, represents an exponential jump function; The first limiting condition is specifically: in, represents the differential of the second parameter, represents the differential of the third parameter, represents the third parameter, represents the jump intensity, a represents a constant, represents the affine diffusion structure, represents an affine diffusion structure; The boundary conditions of the second parameter and the third parameter include: When the variable is 0, the second parameter and the third parameter are both 0; The second parameter and the third parameter are: in, Represents the second parameter, Represents the third parameter, represents the jump intensity, represents the affine diffusion structure, where a, b, c, and d are all constants.

2. A device for establishing a model for predicting uncertain events, characterized in that: include: a building module configured to build a first predictive survival probability model using a Cox process with random intensity; an affine diffusion module, configured to add an affine diffusion process to the first predicted survival probability model to obtain a second predicted survival probability model; A building module configured to build a Feller function on a first parameter of a second prediction survival probability model in combination with an exponential jump function; A setting module is configured to set the second parameter and the third parameter of the second predicted survival probability model to meet the first limiting condition according to the exponential distribution expectation; A calculation module, configured to calculate the second parameter and the third parameter according to the boundary conditions of the second parameter and the third parameter in combination with the first limiting condition; A calculation module is configured to calculate a predicted survival probability model by combining the second parameter, the third parameter, the Feller function and the second predicted survival probability model; and use the predicted survival probability model to predict the survival probability of an individual currently aged x years old t years later; The first prediction survival probability model is specifically: in, represents the survival probability of an individual aged x after t years, represents the future life span of an individual aged x, express , Indicates the time Non-negative mortality intensity function when ; The affine diffusion process satisfies the following formula: in, represents the affine diffusion process, represents the affine diffusion structure, represents the affine diffusion structure, represents Brownian motion; The Feller function is specifically: in, represents the first parameter, represents a constant, represents the volatility parameter, represents the mortality intensity function with volatility, represents an exponential jump function; The first limiting condition is specifically: in, represents the differential of the second parameter, represents the differential of the third parameter, represents the third parameter, represents the jump intensity, a represents a constant, represents the affine diffusion structure, represents an affine diffusion structure; The boundary conditions of the second parameter and the third parameter include: When the variable is 0, the second parameter and the third parameter are both 0; The second parameter and the third parameter are: in, Represents the second parameter, Represents the third parameter, represents the jump intensity, represents the affine diffusion structure, where a, b, c, and d are all constants.

3. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to claim 1 is implemented.

4. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method of claim 1.

Images