Method and device for determining status data

Abstract

The present invention discloses a method and device for determining state data, and relates to the field of computer technology. A specific implementation of the method includes: determining the state data of the user in the current statistical period based on the user's behavior data in the current statistical period; using the user's state data in the current statistical period, the time length data from the predetermined future moment to the current statistical period, and the state transition probability matrix of the user obtained in advance to determine the probability distribution information of the user's state data at the future moment; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods. This implementation can determine the state of the user at the future moment according to the user's current state and the predetermined state transition probability matrix.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for determining status data. Background Art

[0002] In actual work, it is necessary to understand the user's state at a certain moment in the future based on his current state in order to execute corresponding decisions. Existing technology cannot meet this requirement. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and apparatus for determining state data, which can determine the state of a user at a future moment according to the current state of the user and a predetermined state transition probability matrix.

[0004] To achieve the above objective, according to one aspect of the present invention, a method for determining status data is provided.

[0005] The method for determining status data in an embodiment of the present invention includes: determining the status data of the user in the current statistical period based on the user's behavior data in the current statistical period; using the user's status data in the current statistical period, the time length data from a predetermined future moment to the current statistical period, and the user's state transition probability matrix acquired in advance to determine the probability distribution information of the user's state data at the future moment; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods.

[0006] Optionally, the method further includes: determining the state data of the user in the multiple historical statistical periods based on the behavior data of the user in the multiple historical statistical periods, and obtaining the number of occurrences of each state transition mode occurring in adjacent historical statistical periods; determining the quotient of the number of occurrences of any state transition mode and the total number of occurrences of all state transition modes related to the state transition mode as the transition probability information of any state transition mode; wherein the state transition mode related to any state transition mode and any state transition mode start from the same state data of the user.

[0007] Optionally, each historical statistical cycle has the same duration as the current statistical cycle; and, using the state data of the user in the current statistical cycle, the duration data from a predetermined future moment to the current statistical cycle, and the state transition probability matrix of the user acquired in advance, determining the probability distribution information of the state data of the user at the future moment, including: converting the state data of the user in the current statistical cycle into a current state vector; using the duration data from the future moment to the current statistical cycle to determine the number of statistical cycles distributed between the future moment and the current statistical cycle; multiplying the current state vector by at least one state transition probability matrix of the user to obtain the state vector of the user at the future moment; wherein each component in the state vector represents the probability of occurrence of a state data of the user at the future moment, and the number of state transition probability matrices multiplied by the current state vector is equal to the number of statistical cycles.

[0008] Optionally, the method is used to determine whether to display the information object to the user; and the method further includes: determining whether the predetermined historical tag data of the user matches the information object to be displayed; if so, determining the status data of the user in the multiple historical statistical periods based on the user's behavior data in the multiple historical statistical periods.

[0009] Optionally, the user's state data includes an expected state and / or at least one undesired state; the user's behavior data is multi-dimensional data related to the information object to be displayed, and each dimension is pre-configured with a weight value.

[0010] Optionally, determining the status data of the user in the current statistical period based on the behavior data of the user in the current statistical period includes: determining a weighted calculation result of the behavior data of each dimension of the user in the current statistical period; when the weighted calculation result meets a preset condition, determining the status data of the user in the current statistical period as an expected state; when the weighted calculation result does not meet the said condition, determining the status data of the user in the current statistical period as an undesirable state.

[0011] Optionally, the method further includes: determining whether the probability of the user's expected state at the future moment is greater than a preset threshold; if so, displaying the information object to be displayed to the user.

[0012] To achieve the above objective, according to another aspect of the present invention, a device for determining status data is provided.

[0013] The device for determining status data of an embodiment of the present invention may include: a current status judgment unit, used to determine the status data of the user in the current statistical period based on the user's behavior data in the current statistical period; a future status judgment unit, used to determine the probability distribution information of the user's status data at the future moment using the user's status data in the current statistical period, the duration data from a predetermined future moment to the current statistical period, and the state transition probability matrix of the user acquired in advance; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods.

[0014] To achieve the above objective, according to another aspect of the present invention, an electronic device is provided.

[0015] An electronic device of the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining status data provided by the present invention.

[0016] To achieve the above objective, according to yet another aspect of the present invention, a computer-readable storage medium is provided.

[0017] A computer-readable storage medium of the present invention stores a computer program, and when the program is executed by a processor, the method for determining state data provided by the present invention is implemented.

[0018] According to the technical solution of the present invention, one embodiment of the above invention has the following advantages or beneficial effects: determining the historical state of the user based on the behavioral data of the user in the historical statistical period, and obtaining the state transition probability matrix of the user state transition process (which is a Markov process) by statistically analyzing the transition mode of the historical state, and combining the user's current state with the state transition probability matrix to understand the user's state at the future moment, thereby facilitating the execution of corresponding decisions.

[0019] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0021] Figure 1 is a schematic diagram of the main steps of the method for determining status data in an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of user state transition in an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of user state transfer relations in an embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of specific execution steps of the method for determining status data in an embodiment of the present invention;

[0025] Figure 5 is a schematic diagram of components of an apparatus for determining status data in an embodiment of the present invention;

[0026] Figure 6 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0027] Figure 7 The present invention is a schematic diagram of the structure of an electronic device used to implement the method for determining status data in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0029] In some work scenarios, it is necessary to judge the state of the user at a future moment according to the user's current state. The existing technology is difficult to meet this requirement. The present invention can achieve this purpose through a state judgment method based on a Markov process. Markov process is a type of random process. The state at any moment in the process is determined only by one or more previous states, and is independent of the earlier state. The Markov process in which both time and state take discrete values ​​is a Markov chain. In a Markov chain, the state at a future moment can be calculated by the current state and the state transition probability matrix. In addition, in the following description, the user state can be the state embodied by the user when performing related transactions. For example, when shopping, the user can be in a high-activity state, a stable state, or a low-activity state (the activity levels of the three decrease in turn), and these three states can be referred to as different state data below. It can be understood that the number and content of the state data can be set according to actual needs, and the above high-activity state, stable state, or low-activity state are only examples. It should be pointed out that the embodiments of the present invention and the technical features in the embodiments can be combined with each other without conflict.

[0030] Figure 1 4 is a schematic diagram of main steps of a method for determining status data according to an embodiment of the present invention.

[0031] like Figure 1As shown, the method for determining status data in the embodiment of the present invention can be specifically performed according to the following steps:

[0032] Step S101: determining the status data of the user in the current statistical period according to the behavior data of the user in the current statistical period.

[0033] In an embodiment of the present invention, multiple statistical periods can be set to perform periodic statistics on user behavior data. The current statistical period is the statistical period at the current moment, and the statistical period earlier than the current statistical period is the historical statistical period. It can be understood that the current statistical period and each historical statistical period can be a continuous time period or a discontinuous time period, and can also have the same duration or different durations. Preferably, the current statistical period and each historical statistical period are continuous time periods with the same duration. For example, if the statistical period is one month in length and the current moment is a certain moment in January of a certain year, then each month of the previous year is a historical statistical period.

[0034] User behavior data may be user data of multiple dimensions for related transactions. For example, when the related transaction is to determine the user's shopping activity status, the user behavior data may involve the following dimensions: the number of times the related items are browsed, whether the related items are followed, whether the item provider is followed, etc. The user's status data in any statistical period can be determined through the user behavior data of the statistical period. Specifically, the weighted calculation result of the user's behavior data of each dimension in any statistical period is calculated, such as the weighted sum. When the weighted calculation result meets the preset conditions (for example, greater than the preset threshold value), the user's status data in the statistical period is determined as the expected state; when the weighted calculation result does not meet the preset conditions (for example, not greater than the threshold value), the user's status data in the statistical period is determined as an undesirable state. Among them, the expected state can be the aforementioned high-activity state, and the undesirable state can be the aforementioned stable state or low-activity state. It should be noted that user behavior data can be determined according to specific scenarios. For example, in the scenario of determining whether to display an information object (such as an online advertisement) to a user, user behavior data may be browsing, attention, and other data related to the category of the item carried by the information object. The above categories can be determined to various granularities as needed. For example, when the item carried by the information object is a certain brand of women's clothing, women's clothing can be used as the above category, or clothing with a coarser granularity or the entire category covering all items can be used as the above category.

[0035] Before executing step S101, a state transition probability matrix formed by user state transitions in multiple historical statistical periods can be calculated. It can be understood that due to the influence of periodic events, user states often show periodic changes, and the process of user state transition can be considered as a Markov process or a Markov chain. For example, the user's shopping state often follows the monthly salary payment and presents a monthly cycle transition, and this state transition process can be considered as a Markov chain. Figure 2 Schematic diagram of user state transition in an embodiment of the present invention. Figure 2 As shown in the figure, each box represents the status data of a user in a certain month in the historical period, i.e., a certain historical statistical period. Two adjacent boxes correspond to two adjacent historical statistical periods. The arrow points to the direction of time advancement. D1 represents a high-activity state, D2 represents a stable state, and D3 represents a low-activity state. Figure 2 As can be seen from the figure, there are 9 types of state transitions that occur in any two adjacent historical statistical periods, namely from D1 to D1, from D1 to D2, from D1 to D3, from D2 to D1, from D2 to D2, from D2 to D3, from D3 to D1, from D3 to D2, and from D3 to D3. These nine user state transitions are as follows: Figure 3 shown.

[0036] The state transition probability matrix can be determined by counting the number of times each state transition mode appears in the historical statistical period. Among them, each element in the state transition probability matrix is ​​the transition probability information of each state transition mode. For any state transition mode, its transition probability information is the quotient of the number of occurrences of the state transition mode and the total number of occurrences of all state transition modes related to the state transition mode. In an embodiment of the present invention, the state transition mode related to the state transition mode refers to a state transition mode that starts with the same state data as the state transition mode. For example, for the state transition mode from D1 to D2, its related state transition modes are: a state transition mode from D1 to D1, a state transition mode from D1 to D2, and a state transition mode from D1 to D3. In other words, for the state transition mode from the first state data to the second state data (the first state data and the second state data are both any state data), first, the number of occurrences of the state transition mode from the first state data to the second state data and the total number of occurrences of all state transition modes starting from the first state data can be determined, and then the former can be divided by the latter to obtain the transition probability information of the state transition mode from the first state data to the second state data. The above method can be used to determine the transition probability information of each state transition mode, thereby determining the state transition probability matrix.

[0037] by Figure 2 For example, Figure 2There are 14 historical statistical cycles in the data, and the number of occurrences of each state transition mode is shown in the following table:

[0038]

[0039]

[0040] Using the above calculation method, the state transition probability matrix can be obtained as follows:

[0041]

[0042] Among them, the first row to the third row correspond to D1, D2, and D3 respectively, and the first column to the third column correspond to D1, D2, and D3 respectively. Each element represents the transition probability of the state transition mode from the row to the column.

[0043] Step S102: Determine the probability distribution information of the user's state data at a future time by using the user's state data at a current statistical period, the duration data from a predetermined future time to the current statistical period, and the user's state transition probability matrix acquired in advance.

[0044] In order to calculate the probability distribution information of the user's state data at future moments, in this step, the state data of the user in the current statistical period is first converted into the current state vector. Generally, the current state vector is a row vector that can be multiplied with the state transition probability matrix. For example, if the state data of the user in the current statistical period is a highly active state, it is converted into the current state vector (1, 0, 0); if the state data of the user in the current statistical period is a stable state, it is converted into the current state vector (0, 1, 0); if the state data of the user in the current statistical period is a low-activity state, it is converted into the current state vector (0, 0, 1). In addition, it is necessary to calculate the number of statistical periods distributed from the current statistical period to the future moment, that is, the length of the current statistical period from the future moment (the length of time between the end point of the current statistical period at a later time and the future moment can be used in the specific calculation) divided by the length of the statistical period and the calculation result is adjusted. Also with Figure 2 Taking the scenario shown as an example, if the current statistical period is February and the expected future moment is a certain moment in April of the same year, the duration from the current statistical period to the future moment is one month plus a certain number of days. At this time, the number of statistical periods calculated is a decimal between 1 and 2. Rounding it up to 2 is the number of statistical periods distributed from the current statistical period to the future moment.

[0045] After obtaining the user's current state vector and the number of statistical cycles, the current state vector can be multiplied by at least one state transition probability matrix to obtain the user's state vector at the future moment. It can be understood that each component in the state vector at the future moment represents the probability of occurrence of a state data corresponding to the user at the future moment, and the number of state transition probability matrices multiplied by the current state vector is equal to the number of statistical cycles, so that the probability distribution information of the user's state data at the future moment is obtained. For example, in the above example, if the user's current state vector is (1, 0, 0), then its state vector at the future moment is calculated by the following formula:

[0046]

[0047] Among them, (1 / 3, 1 / 2, 1 / 6) is the state vector of the user in March. (15 / 36, 25 / 72, 17 / 72) is the state vector of the user in April, that is, the state vector at the future moment. 15 / 36 is the probability of occurrence corresponding to the high-activity state, 25 / 72 is the probability of occurrence corresponding to the stable state, and 17 / 72 is the probability of occurrence corresponding to the low-activity state. Subsequent decisions can be made based on the above calculation results.

[0048] Figure 4 is a schematic diagram of specific execution steps of the method for determining status data in an embodiment of the present invention, Figure 4 The steps shown are execution steps for applying the above method for determining status data to the information object display scenario. The information object refers to a data object or virtual information in a specific form as an information carrier, such as an online advertisement (an online advertisement refers to an advertisement using a web page on the Internet as a carrier). It can be understood that the above scenario is only one of the applicable scenarios of the method for determining status data of the present invention.

[0049] In an embodiment of the present invention, it is necessary to determine the users who are suitable for information object display at a predetermined future moment. The specific steps are as follows: first, select candidate users according to the degree of match between the user's historical tag data and the information object (i.e., the portrait data obtained according to the user's historical behavior data), remove users with a lower degree of match, and execute the next step for users with a higher degree of match. For example, if the information object is laundry detergent, users with labels such as housewife and middle-aged have a higher degree of match with the information object, and the next step can be executed for these users. Next, the state transition probability matrix and the current state matrix of each user are determined using the above method, and the state transition probability matrix and the current state matrix are used to calculate and determine the probability distribution of the user's state data at the future moment. Finally, the state data probability distribution is used to select the target user for information object display, for example, the user whose probability of occurrence of the highly active state is greater than the preset threshold is determined as the target user. Through the above settings, data analysis can be performed based on the user's state transition rules or more accurate information object delivery can be achieved.

[0050] In the technical solution of the embodiment of the present invention, the historical state of the user is determined based on the behavioral data of the user in the historical statistical period, and the state transition probability matrix of the user state transition process can be obtained by counting the transition mode of the historical state. The user's current state is combined with the state transition probability matrix to understand the user's state at the future moment, thereby facilitating the execution of corresponding decisions.

[0051] It should be noted that, for the convenience of description, the aforementioned method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, and some steps can actually be performed in other sequences or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the present invention.

[0052] In order to better implement the above-mentioned solution of the embodiment of the present invention, relevant devices for implementing the above-mentioned solution are also provided below.

[0053] See also Figure 5 As shown, the apparatus 500 for determining state data provided by the embodiment of the present invention may include: a current state determination unit 501 and a future state determination unit 502 .

[0054] Among them, the current state judgment unit 501 can be used to determine the state data of the user in the current statistical period based on the user's behavior data in the current statistical period; the future state judgment unit 502 can be used to use the user's state data in the current statistical period, the duration data of the predetermined future time from the current statistical period, and the state transition probability matrix of the user obtained in advance to determine the probability distribution information of the user's state data at the future time; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods.

[0055] In an embodiment of the present invention, the device 500 may further include a historical state judgment unit, which is used to: determine the state data of the user in the multiple historical statistical periods based on the user's behavior data in the multiple historical statistical periods, and obtain the number of occurrences of each state transition mode occurring in adjacent historical statistical periods; determine the quotient of the number of occurrences of any state transition mode and the total number of occurrences of all state transition modes related to the state transition mode as the transition probability information of any state transition mode; wherein the state transition mode related to any state transition mode and any state transition mode start from the same state data of the user.

[0056] In a specific application, each historical statistical period has the same duration as the current statistical period; the future state judgment unit 502 can be further used to: convert the state data of the user in the current statistical period into a current state vector; determine the number of statistical periods distributed between the future moment and the current statistical period using the duration data of the future moment from the current statistical period; multiply the current state vector by at least one state transition probability matrix of the user to obtain the state vector of the user at the future moment; wherein each component in the state vector represents the probability of occurrence of a state data corresponding to the user at the future moment, and the number of state transition probability matrices multiplied by the current state vector is equal to the number of statistical periods.

[0057] In some embodiments, the device 500 can be used to determine whether to display an information object to the user; the device 500 may further include a preprocessing unit, which is used to: determine whether the predetermined historical tag data of the user matches the information object to be displayed; if so, determine the status data of the user in the multiple historical statistical periods based on the user's behavior data in the multiple historical statistical periods.

[0058] In an optional implementation, the user's state data includes an expected state and / or at least one undesired state; the user's behavior data is multi-dimensional data related to the information object to be displayed, and each dimension is pre-configured with a weight value.

[0059] In actual application scenarios, the current state judgment unit 501 can be further used to: determine the weighted calculation result of the user's behavior data in each dimension in the current statistical period; when the weighted calculation result meets the preset conditions, determine the state data of the user in the current statistical period as an expected state; when the weighted calculation result does not meet the conditions, determine the state data of the user in the current statistical period as an undesirable state.

[0060] In addition, in an embodiment of the present invention, the device 500 may further include an information object display unit, which is used to: determine whether the probability of the user's expected state at the future moment is greater than a preset threshold; if so, display the information object to be displayed to the user.

[0061] In the technical solution of the embodiment of the present invention, the historical state of the user is determined based on the behavioral data of the user in the historical statistical period, and the state transition probability matrix of the user state transition process can be obtained by counting the transition mode of the historical state. The user's current state is combined with the state transition probability matrix to understand the user's state at the future moment, thereby facilitating the execution of corresponding decisions.

[0062] Figure 6 An exemplary system architecture 600 is shown to which the method for determining status data or the apparatus for determining status data according to the embodiments of the present invention can be applied.

[0063] like Figure 6 As shown, the system architecture 600 may include terminal devices 601, 602, 603, a network 604 and a server 605 (this architecture is only an example, and the components included in the specific architecture may be adjusted according to the specific application). The network 604 is used to provide a medium for a communication link between the terminal devices 601, 602, 603 and the server 605. The network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0064] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various client applications can be installed on the terminal devices 601, 602, 603, such as a user status determination application (only an example).

[0065] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0066] The server 605 may be a server that provides various services, such as a computing server (only an example) that provides support for a user status determination application operated by a user using the terminal devices 601, 602, and 603. The computing server may process the received user status determination request and feed back the processing result (such as the calculated user status - only an example) to the terminal devices 601, 602, and 603.

[0067] It should be noted that the method for determining status data provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for determining status data is generally disposed in the server 605 .

[0068] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0069] The present invention also provides an electronic device. The electronic device of an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining state data provided by the present invention.

[0070] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of an electronic device suitable for implementing an embodiment of the present invention. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0071] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0072] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0073] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit 701, the above functions defined in the system of the present invention are executed.

[0074] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0075] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0076] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a current state judgment unit and a future state judgment unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the current state judgment unit may also be described as "a unit that provides the future state judgment unit with the state data of the user in the current statistical period".

[0077] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently and not be installed in the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the steps executed by the device include: determining the state data of the user in the current statistical period based on the user's behavior data in the current statistical period; using the user's state data in the current statistical period, the time length data from the predetermined future moment to the current statistical period, and the state transition probability matrix of the user obtained in advance to determine the probability distribution information of the user's state data at the future moment; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods.

[0078] In the technical solution of the embodiment of the present invention, the historical state of the user is determined based on the behavioral data of the user in the historical statistical period, and the state transition probability matrix of the user state transition process can be obtained by counting the transition mode of the historical state. The user's current state is combined with the state transition probability matrix to understand the user's state at the future moment, thereby facilitating the execution of corresponding decisions.

[0079] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining status data, characterized in that include: Determine the user's status data in the current statistical period based on the user's behavior data in the current statistical period; Determining probability distribution information of the state data of the user at the future moment by using the state data of the user in the current statistical period, the time length data from the scheduled future moment to the current statistical period, and the state transition probability matrix of the user acquired in advance, including: converting the state data of the user in the current statistical period into a current state vector; determining the number of statistical periods distributed between the future moment and the current statistical period by using the time length data from the future moment to the current statistical period; and multiplying the current state vector by at least one state transition probability matrix of the user to obtain the state vector of the user at the future moment; The state transition probability matrix includes: transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods.

2. The method according to claim 1, characterized in that The method further comprises: Determine the state data of the user in the multiple historical statistical periods according to the behavior data of the user in the multiple historical statistical periods, and obtain the number of occurrences of each state transition mode occurring in adjacent historical statistical periods; The quotient of the number of occurrences of any state transition mode and the total number of occurrences of all state transition modes related to the state transition mode is determined as the transition probability information of the any state transition mode; wherein the state transition mode related to the any state transition mode and the any state transition mode start from the same state data of the user.

3. The method according to claim 2, characterized in that Each historical statistical cycle has the same length as the current statistical cycle; each component of the state vector of the user at the future moment represents the probability of occurrence of a state data corresponding to the user at the future moment, and the number of state transition probability matrices multiplied by the current state vector is equal to the number of statistical cycles.

4. The method according to claim 3, characterized in that The method is used to determine whether to display the information object to the user; and the method further comprises: Determine whether the predetermined historical tag data of the user matches the information object to be displayed; If so, the status data of the user in the multiple historical statistical periods are determined according to the behavior data of the user in the multiple historical statistical periods.

5. The method according to claim 4, characterized in that The user's state data includes a desired state and / or at least one undesired state; The user's behavior data is multi-dimensional data related to the information object to be displayed, and each dimension is pre-configured with a weight value.

6. The method according to claim 5, characterized in that Determine the user's status data in the current statistical period based on the user's behavior data in the current statistical period, including: Determine the weighted calculation results of each dimension of the user's behavior data in the current statistical period; When the weighted calculation result meets the preset condition, the state data of the user in the current statistical period is determined as the expected state; When the weighted calculation result does not satisfy the condition, the state data of the user in the current statistical period is determined as an undesirable state.

7. The method according to claim 6, characterized in that The method further comprises: Determine whether the probability of the user's expected state at the future time is greater than a preset threshold: if so, display the information object to be displayed to the user.

8. A device for determining status data, characterized in that include: A current status determination unit, used to determine the status data of the user in the current statistical period according to the behavior data of the user in the current statistical period; A future state judgment unit is used to determine the probability distribution information of the state data of the user at the future moment by using the state data of the user in the current statistical period, the time length data of the predetermined future moment from the current statistical period, and the state transition probability matrix of the user obtained in advance; wherein the state transition probability matrix includes: the transition probability information of each state transition mode of the user in adjacent historical statistical periods in multiple historical statistical periods; The future state judgment unit is also used to: convert the state data of the user in the current statistical period into a current state vector; determine the number of statistical periods distributed between the future moment and the current statistical period using the time length data from the future moment to the current statistical period; and multiply the current state vector by at least one state transition probability matrix of the user to obtain the state vector of the user at the future moment.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images