A data analysis method, apparatus, electronic device, and storage medium

Abstract

This invention provides a data analysis method, apparatus, electronic device, and storage medium. It acquires text data and numerical data for multiple users; decouples the text data to generate text-numerical data; determines a preset decision type; calculates decision coefficients for the preset decision type based on the text-numerical data and numerical data; the preset decision type has multiple corresponding decision schemes; and determines the target decision scheme from the multiple decision schemes using the decision coefficients. This enhances the personalization of the hotel operation decision analysis process, utilizes text data resources more efficiently, and further improves the accuracy of hotel operation data analysis results.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a data analysis method, a data analysis device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Hotel management decision analysis is a decision analysis conducted on the strategic operations of the entire hotel. Existing hotel management decision analysis is usually based on external data, such as the number of flight bookings, flight prices, and room rates of similar hotels in the surrounding area. It does not include textual information variables of hotel members in the analysis, resulting in insufficient relevance and comprehensiveness of the analysis results. At the same time, after providing the analysis results, there is a lack of effective means to examine the effects and benefits, and to optimize the decisions based on the examination. This limits the development of personalization and self-optimization in the hotel industry or customers in the process of hotel management decision analysis.

[0003] Therefore, how to conduct decision analysis, evaluation, and optimization for hotel operations to improve the accuracy and scientific nature of hotel operation decision analysis is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The present invention provides a data analysis method, apparatus, electronic device, and computer-readable storage medium to solve the problem of how to analyze and make decisions based on hotel operating data.

[0005] This invention discloses a data analysis method, which may include:

[0006] Retrieve text and numerical data from multiple users;

[0007] By decoupling the text data, text numerical data is generated;

[0008] A preset decision type is determined, and a decision coefficient for the preset decision type is calculated based on the text numerical data and the numerical data; the preset decision type has multiple corresponding decision schemes.

[0009] The target decision scheme is determined from multiple decision schemes using the decision coefficients.

[0010] Optionally, the text data and the numerical data each have corresponding timestamps and data types; multiple users have one-to-one corresponding user identifiers, and the step of calculating the decision coefficient for the preset decision type based on the text data and the numerical data may include:

[0011] The text numerical data and the numerical data are coupled based on corresponding timestamps and data types to generate an array matrix for multiple users;

[0012] Based on the preset decision type, target text numerical data and target numerical data that are associated with the preset decision type are determined from the array matrix; the target text numerical data and the target numerical data each have a corresponding target timestamp and target data type.

[0013] A first curve is generated using the target timestamp, the target text numerical data, and the target numerical data; the first curve is used to express the changes in target text numerical data and target numerical data corresponding to different target data types under a preset time sequence.

[0014] A second curve is generated using the target timestamp, the user identifier, the target text numerical data, and the target numerical data; the second curve is used to express the changes in the target text numerical data and the target numerical data under the same target data type corresponding to different user identifiers under a preset time sequence.

[0015] The decision coefficients for the preset decision type are calculated using the first curve and the second curve.

[0016] Optionally, the step of calculating the decision coefficients for the preset decision type using the first curve and the second curve may include:

[0017] The target text numerical data and the frequency of variables corresponding to different timestamps are calculated based on the first curve, and a constant value is generated based on the variable frequency according to the first preset rule.

[0018] The number of curves in the second curve is determined based on the user identifier;

[0019] Determine the curve intersection points for the second curve, and determine the target number of intersection points from the curve intersection points according to the second preset rule;

[0020] Dynamic coefficients are generated based on the number of target intersection points and the number of curves.

[0021] Decision coefficients for the preset decision type are generated using the dynamic coefficients and the constant values.

[0022] Optionally, the step of determining the target decision scheme from the multiple decision schemes using the decision coefficients may include:

[0023] A third curve is generated using multiple decision coefficients and the target timestamp; the third curve is used to express the changes in the decision coefficients corresponding to multiple decision schemes under a preset time sequence;

[0024] The target time data is determined based on the third curve, and the corresponding target decision coefficient is determined based on the target time data.

[0025] The decision scheme corresponding to the target decision coefficient is taken as the target decision scheme.

[0026] Optionally, it may also include:

[0027] Calculate the first deviation magnitude value for the target decision coefficient according to the first preset time period;

[0028] If the first deviation magnitude is less than the minimum threshold, the target decision scheme is deemed effective.

[0029] If the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold, then the second deviation magnitude value is calculated for the target decision coefficient according to the second preset time period;

[0030] If the first deviation value is greater than the highest threshold, the target decision scheme is determined to be invalid.

[0031] This invention also discloses a data analysis device, which may include:

[0032] The data acquisition module is used to acquire text and numerical data from multiple users.

[0033] The text numerical data generation module is used to generate text numerical data by decoupling the text data;

[0034] The decision coefficient calculation module is used to determine a preset decision type and calculate the decision coefficient for the preset decision type based on the text numerical data and the numerical data; the preset decision type has multiple corresponding decision schemes.

[0035] The target decision scheme determination module is used to determine the target decision scheme from multiple decision schemes using the decision coefficients.

[0036] Optionally, the text data and the numerical data each have corresponding timestamps and data types; multiple users have one-to-one corresponding user identifiers, and the decision coefficient calculation module may include:

[0037] The array matrix generation submodule is used to couple the text numerical data and the numerical data based on the corresponding timestamp and data type to generate an array matrix for multiple users;

[0038] The association determination submodule is used to determine, from the array matrix, target text numerical data and target numerical data that are associated with the preset decision type according to the preset decision type; the target text numerical data and the target numerical data respectively have corresponding target timestamps and target data types;

[0039] The first curve generation submodule is used to generate a first curve using the target timestamp, the target text numerical data, and the target numerical data; the first curve is used to express the changes in target text numerical data and target numerical data corresponding to different target data types under a preset time sequence.

[0040] The second curve generation submodule is used to generate a second curve using the target timestamp, the user identifier, the target text numerical data, and the target numerical data; the second curve is used to express the changes in target text numerical data and target numerical data under the same target data type corresponding to different user identifiers under a preset time sequence.

[0041] The decision coefficient calculation submodule is used to calculate the decision coefficient for the preset decision type using the first curve and the second curve.

[0042] Optionally, the decision coefficient calculation submodule may include:

[0043] A constant value generation unit is used to calculate the target text numerical data and the frequency of variables corresponding to different timestamps based on the first curve, and generate constant values ​​based on the variable frequencies according to a first preset rule.

[0044] A curve number determination unit is used to determine the number of curves in the second curve based on the user identifier;

[0045] The curve intersection point determination unit is used to determine the curve intersection points for the second curve, and to determine the target number of intersection points from the curve intersection points according to a second preset rule;

[0046] The dynamic coefficient generation unit is used to calculate and generate dynamic coefficients based on the number of target intersection points and the number of curves;

[0047] The decision coefficient generation unit is used to generate decision coefficients for the preset decision type using the dynamic coefficients and the constant values.

[0048] Optionally, the target decision scheme determination module may include:

[0049] The third curve generation submodule is used to generate a third curve using multiple decision coefficients and the target timestamp; the third curve is used to express the changes in decision coefficients corresponding to multiple decision schemes under a preset time sequence;

[0050] The target decision coefficient determination submodule is used to determine the target time data based on the third curve and to determine the corresponding target decision coefficient based on the target time data.

[0051] The target decision scheme determination submodule is used to select the decision scheme corresponding to the target decision coefficient as the target decision scheme.

[0052] Optionally, it may also include:

[0053] The first deviation magnitude calculation submodule is used to calculate the first deviation magnitude value for the target decision coefficient according to a first preset time period.

[0054] The effective determination submodule is used to determine that the target decision scheme is effective if the first deviation amplitude value is less than the minimum threshold.

[0055] The second deviation magnitude calculation submodule is used to calculate the second deviation magnitude value for the target decision coefficient according to the second preset time period if the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold.

[0056] The invalidity determination submodule is used to determine that the target decision scheme is invalid if the first deviation magnitude value is greater than the highest threshold.

[0057] This invention also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0058] The memory is used to store computer programs;

[0059] When the processor executes a program stored in the memory, it implements the method described in the embodiments of the present invention.

[0060] This invention also discloses a computer-readable storage medium storing instructions that, when executed by one or more processors, cause the processors to perform the methods described in this invention.

[0061] The embodiments of the present invention have the following advantages:

[0062] This invention, through acquiring text and numerical data from multiple users; decoupling the text data to generate text-numerical data; determining a preset decision type; calculating decision coefficients for the preset decision type based on the text-numerical data and numerical data; recognizing multiple decision schemes corresponding to the preset decision type; and determining the target decision scheme from the multiple decision schemes using the decision coefficients, thereby enhancing personalization in the hotel operation decision analysis process, utilizing text data resources more efficiently, and further improving the accuracy of hotel operation data analysis results. Attached Figure Description

[0063] Figure 1 This is a flowchart of the steps of a data analysis method provided in an embodiment of the present invention;

[0064] Figure 2 This is a schematic diagram of a structure for a first curve provided in an embodiment of the present invention;

[0065] Figure 3 This is a schematic diagram of a structure for the second curve provided in an embodiment of the present invention;

[0066] Figure 4 This is a schematic diagram of a structure for a third curve provided in an embodiment of the present invention;

[0067] Figure 5 This is a flowchart of another data analysis method provided in this embodiment of the invention;

[0068] Figure 6 This is a structural block diagram of a data analysis device provided in an embodiment of the present invention;

[0069] Figure 7 This is a hardware structure block diagram of an electronic device provided in various embodiments of the present invention. Detailed Implementation

[0070] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0071] With the digital transformation of the hotel industry, large and medium-sized hotels and chain hotels have established exclusive membership systems for business development. Through online marketing and offline promotional activities, they are continuously expanding their membership base and accumulating vast amounts of member information. Hotels currently often use members as a target group of high-quality consumers for marketing analysis and provide them with exclusive and convenient digital stay experiences. Faced with massive amounts of data on hundreds of thousands or even millions of members, and exponentially increasing amounts of different types of information, choosing the right analytical methods to guide different business decisions is becoming an increasingly important focus for hotel management. Currently, the main shortcomings of operational decision-making data analysis in the hotel industry are as follows: Regarding the data types analyzed, existing operational decision-making data analysis primarily uses numerical data, such as prices of similar products, quantities of similar products, actual sales revenue, and various industry operating indicators. It fails to incorporate textual information about members, such as addresses, job positions, employment status, and family members. This wastes valuable information resources and makes the analysis results less rigorous. Regarding analytical methods, existing operational decision-making data analysis mainly compares general values ​​such as actual operating averages and threshold deviations with operational or industry indices to derive scores. Since operational or industry indices are comprehensive indices generated based on the entire industry, the scoring of individual business decision-making plans under existing operational decision-making data analysis methods lacks specificity and accuracy. Furthermore, the aforementioned shortcomings of existing operational decision-making data analysis also increase the difficulty of reviewing the actual implementation results of the final decisions, making effective verification and optimization difficult. Embodiments of the present invention provide a data analysis method, apparatus, electronic device, and storage medium that combine user text data and numerical data to perform data analysis on hotel management decisions, thereby enhancing personalization and self-optimization in the data analysis process for hotel management decisions, utilizing data resources more efficiently, improving the scientific rigor and accuracy of the data analysis method, and further improving the accuracy of the data analysis results.

[0072] Reference Figure 1 The diagram illustrates a flowchart of a data analysis method provided in an embodiment of the present invention, which may specifically include the following steps:

[0073] Step 101: Obtain text and numerical data for multiple users;

[0074] Step 102: Decouple the text data to generate text numerical data;

[0075] Step 103: Determine the preset decision type, and calculate the decision coefficient for the preset decision type based on the text numerical data and the numerical data; the preset decision type has multiple corresponding decision schemes;

[0076] Step 104: Determine the target decision scheme from the multiple decision schemes using the decision coefficients.

[0077] In practical applications, in order to improve the timeliness and relevance of data analysis, textual and numerical data of users can be extracted from the user's membership system with the user's authorization and in compliance with relevant laws and regulations. For example, the membership information in a hotel's membership system is updated every time a member makes a purchase or changes their personal information at the hotel. When the time period, external environment, and personal circumstances change, the member's demand for the products provided by the hotel will also change.

[0078] In a specific implementation, embodiments of the present invention can acquire text data and numerical data from multiple users. For example, the text data can be data displayed in words, such as the employment status, job position, industry, job title, gender, home address, place of origin, ethnicity, family structure, consumption evaluation, and travel trajectory of hotel members. The numerical data can be data displayed in numbers, such as the income range, age, consumption amount, consumption time, and consumption quantity of hotel members.

[0079] Of course, the above examples are merely illustrative, and those skilled in the art can use other types of data as text data or numerical data. In this regard, the embodiments of the present invention do not impose any limitations.

[0080] In practical applications, text data is based on character combinations, while numerical data is based on number combinations. Taking Chinese characters as an example, there are approximately 100,000 existing Chinese characters, far exceeding the number of Arabic numerals "0" to "9". Furthermore, each Chinese character has at least one meaning, and their combinations produce word meanings. Therefore, processing text data is far more difficult and labor-intensive than processing numerical data. Additionally, due to the characteristics of written language, different combinations of Chinese characters may represent the same meaning. For example, changing a user's place of residence from "Beijing" to "Guangzhou" has the same logical meaning as changing it from "Beijing" to "Guangzhou". However, text data is different. In data analysis, treating each character combination as a valid piece of text data would inevitably create a huge computational burden. Therefore, reducing the coupling between text and logic and improving the usability of text data is crucial. In the embodiments of this application, the text content and logical content of text data can be separated through decoupling, generating text-numerical data, which facilitates subsequent data processing and reduces the computational burden.

[0081] In a specific implementation, embodiments of the present invention can generate text numerical data by decoupling text data. For example, when the text data obtained from a user is the "city of residence" of hotel member Zhang San, all the text data of "city of residence" of Zhang San from the time he registered his membership information on January 1, 2010 to the present time can be extracted. The changes in the text data are decoupled and marked by variables and counted, and the counted data is used as the text numerical data. For example, when Zhang San's "city of residence" registered in the membership system changes from "Beijing" to "Guangzhou", the text data of Zhang San's "city of residence" is decoupled from "0" to "1". If it changes again, it is recorded as "α", where "α = number of changes". That is, if Zhang San's city of residence changes from Beijing to Guangzhou and then changes to Shanghai, then "α = 2".

[0082] Of course, the above examples are merely illustrative. Those skilled in the art can use other rules to decouple text data to generate text numerical data, and the embodiments of the present invention do not limit this.

[0083] In a specific implementation, embodiments of the present invention can determine a preset decision type, calculate a decision coefficient for the preset decision type based on textual and numerical data, and determine a target decision type from the multiple decision options using the decision coefficient. For example, the hotel's decision type is determined to be "room type recommendation," which has multiple corresponding decision options, such as "recommend economy single room," "recommend economy double room," and "recommend business suite." Based on member "Zhang San's" textual and numerical data "marital status_α=1" and numerical data "age: 25_income: 8000," the decision coefficient for member "Zhang San" under the "room type recommendation" type is calculated to be 9 for "recommend economy single room," 10 for "recommend economy double room," and 8 for "recommend business suite." Then, the decision coefficients are sorted from largest to smallest, and the first one is taken as the target decision type. That is, "recommend economy double room" is taken as the target decision type for member "Zhang San."

[0084] This invention, in its embodiments, acquires text and numerical data from multiple users; decouples the text data to generate text-numerical data; determines a preset decision type; calculates decision coefficients for the preset decision type based on the text and numerical data; the preset decision type has multiple corresponding decision schemes; and determines the target decision scheme from these multiple schemes using the decision coefficients. This enhances the personalization of the hotel management decision analysis process, utilizes text data resources more efficiently, and further improves the accuracy of hotel management data analysis results.

[0085] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0086] In an optional embodiment of the present invention, the text data and the numerical data each have a corresponding timestamp and data type; the plurality of users have a one-to-one corresponding user identifier, and the step of calculating the decision coefficient for the preset decision type based on the text data and the numerical data includes:

[0087] The text numerical data and the numerical data are coupled based on corresponding timestamps and data types to generate an array matrix for multiple users;

[0088] Based on the preset decision type, target text numerical data and target numerical data that are associated with the preset decision type are determined from the array matrix; the target text numerical data and the target numerical data each have a corresponding target timestamp and target data type.

[0089] A first curve is generated using the target timestamp, the target text numerical data, and the target numerical data; the first curve is used to express the changes in target text numerical data and target numerical data corresponding to different target data types under a preset time sequence.

[0090] A second curve is generated using the target timestamp, the user identifier, the target text numerical data, and the target numerical data; the second curve is used to express the changes in the target text numerical data and the target numerical data under the same target data type corresponding to different user identifiers under a preset time sequence.

[0091] The decision coefficients for the preset decision type are calculated using the first curve and the second curve.

[0092] In specific implementations, the text data and numerical data in the embodiments of the present invention have corresponding timestamps and data types, respectively; multiple users have one-to-one corresponding user identifiers.

[0093] In practical applications, to improve the timeliness and dynamic correlation of data, real-time information can be used. In an optional embodiment of the present invention, text data and numerical data each have corresponding timestamps. The time information when the text data and numerical data are created can be used as timestamps. These timestamps can express the time when the text data and numerical data are created by the user. The timestamps can be millisecond-level timestamps containing millisecond values ​​or timestamps containing dates, etc. That is, they can be expressed using unit time values ​​such as microseconds, milliseconds, centiseconds, minutes, seconds, minutes, hours, days, weeks, months, years, etc. In addition, to enhance personalization in the analysis process, different users can be assigned one-to-one user identifiers, such as user names.

[0094] Of course, the timestamp can also be any other time information. For example, text data and numerical data of multiple users can be obtained according to a certain period, and the acquisition time is the timestamp of the text data and numerical data. The user identifier can also be other unique user information, such as ID card number or membership number, or other identifiers that can correspond one-to-one with users. In this respect, the embodiments of the present invention do not impose any restrictions.

[0095] As a specific example of an embodiment of the present invention, the numerical data for multiple users can be as shown in Table 1.

[0096] Table 1:

[0097] User ID Timestamp Type a Type c …… Zhang San 20220101 numerical value a1 numerical value a1 …… Zhang San 20220102 numerical value a2 numerical value a2 …… Li Si 20220103 Value a3 Value a3 …… Li Si …… …… …… ……

[0098] The text numerical data for multiple users can be shown in Table 2.

[0099] Table 2:

[0100] User ID Timestamp Type b Type d …… Zhang San 20220101 Variable b1 Variable d1 …… Zhang San 20220102 Variable b2 d2 …… Li Si 20220103 Variable b3 Variable d3 …… Li Si …… …… …… ……

[0101] In practical applications, to enhance the synergy between different data and enable data interaction to collaboratively complete data processing tasks, data coupling can be used to couple multiple data sets. Furthermore, to facilitate the application of data to different decision types, matrices can be formed based on the data, which facilitates data extraction and filtering, enhances the ability of multiple sets of data to be transformed for different decision type requirements, and reduces repetitive computational work.

[0102] In a specific implementation, embodiments of the present invention can couple text numerical data and numerical data based on corresponding timestamps and data types to generate an array matrix for multiple users; for example, coupling the user numerical data in Table 1 and the user text numerical data in Table 2 yields the following array matrix for multiple users:

[0103]

[0104] In a specific implementation, embodiments of the present invention can determine target text numerical data and target numerical data that are associated with the preset decision type from an array matrix according to the preset decision type. The target text numerical data and target numerical data each have a corresponding target timestamp and target data type. For example, when the preset decision type is "decision type A", if the data associated with "decision type A" needs to have "variable" and "numerical" attributes, then the target text numerical data associated with "decision type A" can be determined as "variable bn, variable dn...", and the target numerical data associated with "decision type A" can be determined as "numerical an, numerical cn...". Among them, the target text numerical data has a corresponding target timestamp "20220101, 20220102, 20220103...", and a corresponding target data type "type b, type d...". The target numerical data has a corresponding target timestamp "20220101, 20220102, 20220103...", and a corresponding target data type "type a, type c...".

[0105] Of course, the above examples are merely illustrative. Those skilled in the art can use other relationships to determine the target text numerical data and target numerical data that are related to the preset decision type. In this regard, the embodiments of the present invention do not impose any limitations.

[0106] In a specific implementation, embodiments of the present invention can generate a first curve using a target timestamp, target text numerical data, and target numerical data; the first curve is used to express the changes in target text numerical data and target numerical data corresponding to different target data types under a preset time sequence.

[0107] For example, refer to Figure 2 , Figure 2 This is a schematic diagram of a structure for a first curve provided in an embodiment of the present invention. When the corresponding target data types are "Type 1", "Type 2", "Type 3" and "Type 4", the target timestamp is "time unit in sequential time", and the target text numerical data and target numerical data are "Type 1 value, Type 2 value..." and "Type 3 value, Type 4 value..." respectively, the first curve can be generated according to the sequential time. Figure 2 As shown, the first curve is used to express the changes of "Type 1 value, Type 2 value..." and "Type 3 value, Type 4 value..." corresponding to "Type 1", "Type 2", "Type 3" and "Type 4" under the time unit in the sequential time series.

[0108] In practical applications, time-series-based data analysis helps to derive continuous and long-term trends in data, observe changes in different data types over time, and examine their interactions and relationships. Furthermore, by varying the preset time series and timestamps, the time scale can be altered, allowing for more targeted and predictive analysis of different data types based on actual decision-making needs.

[0109] In a specific implementation, embodiments of the present invention can generate a second curve using a target timestamp, a user identifier, target text numerical data, and target numerical data; the second curve is used to express the changes in target text numerical data and target numerical data under the same target data type corresponding to different user identifiers under a preset time sequence.

[0110] For example, refer to Figure 3 , Figure 3 This is a schematic diagram of a structure for a second curve provided in an embodiment of the present invention; when the target timestamp corresponding to the same target data type is "time unit in sequential time sequence", the user identifier is "Member 1", "Member 2", "Member 3" and "Member 4", and the target text numerical data and target numerical data are "Member 1 value, Member 2 value, Member 3 value, Member 4 value...", a second curve can be generated according to the sequential time sequence. Figure 3 As shown, the second curve is used to express the changes of "Member 1 value, Member 2 value, Member 3 value, Member 4 value..." under the same target data type corresponding to "Member 1", "Member 2", "Member 3" and "Member 4" in sequential time sequence.

[0111] In practical applications, time-series-based data analysis is beneficial for deriving continuous and long-term trends in data, observing changes in different user data of the same data type over time, and examining their interactions and relationships. Furthermore, by varying the preset time series and timestamps, the time scale can be altered, allowing for more targeted and predictive analysis of the same data type based on actual decision-making needs.

[0112] In a specific implementation, embodiments of the present invention can calculate the decision coefficient for a preset decision type using a first curve and a second curve. For example, when the preset decision type is "Decision Type A", according to... Figure 2 and Figure 3 The first and second curves in the graph are used to calculate the decision coefficient Σ for "Decision Type A" according to a preset algorithm.

[0113] This invention couples textual numerical data and numerical data based on corresponding timestamps and data types to generate an array matrix for multiple users. Target textual numerical data and target numerical data associated with a preset decision type are determined from the array matrix according to the preset decision type. Each target textual numerical data and target numerical data has a corresponding target timestamp and target data type. A first curve is generated using the target timestamp, the target textual numerical data, and the target numerical data. The first curve expresses the changes in target textual numerical data and target numerical data corresponding to different target data types under a preset time sequence. A second curve is generated using the target timestamp, the user identifier, the target textual numerical data, and the target numerical data. The second curve expresses the changes in target textual numerical data and target numerical data corresponding to the same target data type for different user identifiers under a preset time sequence. A decision coefficient for the preset decision type is calculated using the first curve and the second curve. This improves the timeliness and dynamic correlation of data, enhances the ability to convert multiple sets of data to meet different decision type requirements, reduces repetitive calculations, and enables more targeted and accurate data analysis based on actual decision needs.

[0114] In an optional embodiment of the present invention, the step of calculating the decision coefficients for the preset decision type using the first curve and the second curve includes:

[0115] The target text numerical data and the frequency of variables corresponding to different timestamps are calculated based on the first curve, and a constant value is generated based on the variable frequency according to the first preset rule.

[0116] The number of curves in the second curve is determined based on the user identifier;

[0117] Determine the curve intersection points for the second curve, and determine the target number of intersection points from the curve intersection points according to the second preset rule;

[0118] Dynamic coefficients are generated based on the number of target intersection points and the number of curves.

[0119] Decision coefficients for the preset decision type are generated using the dynamic coefficients and the constant values.

[0120] In a specific implementation, embodiments of the present invention can calculate the target text numerical data and the frequency of variables corresponding to different timestamps based on the first curve, and generate a constant value based on the variable frequency according to a first preset rule; for example, refer to Figure 2Given the first curve, the target text numerical data and target numerical data are "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical..." respectively, and the timestamp is "time unit in sequential time". Calculate the variable frequency M corresponding to different timestamps for "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical...". When the first preset rule is "when the variable frequency is less than 20%, determine the corresponding target numerical data and / or target text numerical data as constants", generate constants N corresponding to the target text numerical data and target numerical data as "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical..." respectively. Here, the constant can be a numerical value representing quantity or a numerical value representing the number of variables, such as "salary = 2000" and / or "change of permanent address = 2", etc.

[0121] Of course, the above examples are merely illustrative. Those skilled in the art can use other rules to generate constant values ​​based on variable frequencies, and the embodiments of the present invention do not impose any limitations on this.

[0122] In a specific implementation, embodiments of the present invention can determine the number of curves in the second curve based on the user identifier; determine the curve intersection points for the second curve, and determine the target number of intersection points from the curve intersection points according to a second preset rule; calculate and generate dynamic coefficients based on the target number of intersection points and the number of curves; the preset decision type has multiple corresponding decision schemes; and generate decision coefficients for multiple decision schemes through dynamic coefficients and constant values.

[0123] For example, refer to Figure 3 The second curve is used, where user identifiers are "Member 1, Member 2, Member 3... Member n". Based on the one-to-one correspondence between user identifiers and curves, the number of curves in the second curve is determined to be "Number of curves = n". According to the second curve, the number of curve intersections on the second curve is determined to be s. Following the second preset rule "intersections with a value range higher than 70%", the target number of intersections is determined to be s*, and the number of curves in the interval is determined to be "Number of curves in the interval = n*". The dynamic coefficient β can be calculated using the formula: Dynamic coefficient β = (High digit value * Intersection count + Low digit value * Intersection count) / Total number of intersections * Total number of curves in the interval". Of course, the above example is only illustrative. Those skilled in the art can use other rules to generate dynamic coefficients based on the target number of intersections and the number of curves. This embodiment of the invention does not limit this. Furthermore, refer to... Figure 2In the first curve, if the target text numerical data and target numerical data are known to be "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical..." respectively, and the timestamp is "time unit in sequential time", calculate the variable frequency M corresponding to different timestamps for "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical...". When the first preset rule is "when the variable frequency is less than 20%, determine the corresponding target numerical data and / or target text numerical data as constants", generate constants corresponding to the target text numerical data and target numerical data as "Type 1 numerical, Type 2 numerical..." and "Type 3 numerical, Type 4 numerical..." respectively. When the preset decision type is "Decision Type A", "Decision Type A" can correspond to multiple decision schemes "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n". For "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n", based on the aforementioned dynamic coefficient β and constants, where the constants can be numerical values ​​representing quantities or numerical values ​​representing variations, such as "Salary = 2000" and / or "Change of Permanent Address = 2", this invention does not impose any limitations. The final decision coefficients for the multiple decision schemes are calculated according to the following formula: "Decision Coefficient 1, Decision Coefficient 2, Decision Coefficient 3, Decision Coefficient 4... Decision Coefficient n", where "Category" corresponds to different target text numerical data and the target data type corresponding to the target numerical data.

[0124] Decision coefficient Σ = category * constant ∧ dynamic coefficient β

[0125] This invention, through its embodiments, calculates the frequency of variables corresponding to different timestamps of the target text numerical data based on a first curve, and generates a constant value based on the variable frequency according to a first preset rule; determines the number of curves in the second curve based on the user identifier; determines the curve intersection points for the second curve, and determines the number of target intersection points from the curve intersection points according to a second preset rule; calculates and generates dynamic coefficients based on the number of target intersection points and the number of curves; and generates decision coefficients for the preset decision type through the dynamic coefficients and the constant value. Thus, based on the constant, dynamic coefficients, and decision coefficients, it achieves correlation analysis of different types of data and derives dynamic values, enabling the data to have higher accuracy within a specified period.

[0126] In an optional embodiment of the present invention, the step of determining the target decision scheme from the plurality of decision schemes using the decision coefficients includes:

[0127] A third curve is generated using multiple decision coefficients and the target timestamp; the third curve is used to express the changes in the decision coefficients corresponding to multiple decision schemes under a preset time sequence;

[0128] The target time data is determined based on the third curve, and the corresponding target decision coefficient is determined based on the target time data.

[0129] The decision scheme corresponding to the target decision coefficient is taken as the target decision scheme.

[0130] refer to Figure 4 , Figure 4 This is a schematic diagram of a structure for a third curve provided in an embodiment of the present invention.

[0131] In a specific implementation, embodiments of the present invention can generate a third curve using multiple decision coefficients and a target timestamp; the third curve is used to express the changes in decision coefficients corresponding to multiple decision schemes under a preset time sequence; for example, refer to Figure 3 The second curve is used, where user identifiers are "Member 1, Member 2, Member 3... Member n". Based on the one-to-one correspondence between user identifiers and curves, the number of curves in the second curve is determined to be "Number of curves = n". According to the second curve, the number of curve intersections on the second curve is determined to be s. Following the second preset rule "intersections with a value range higher than 70%", the target number of intersections is determined to be s*, and the number of curves in the interval is determined to be "Number of curves in the interval = n*". The dynamic coefficient β can be calculated using the formula: Dynamic coefficient β = (High digit value * Intersection count + Low digit value * Intersection count) / Total number of intersections * Total number of curves in the interval". Of course, the above example is only illustrative. Those skilled in the art can use other rules to generate dynamic coefficients based on the target number of intersections and the number of curves. This embodiment of the invention does not limit this. Furthermore, refer to... Figure 2In the first curve, if the target text numerical data and target numerical data are known as “Type 1 numerical, Type 2 numerical, ... Type n numerical” and “Type 3 numerical, Type 4 numerical, ... Type n numerical” respectively, and the timestamp is “time unit in sequential time sequence”, calculate the variable frequency M corresponding to different timestamps for “Type 1 numerical, Type 2 numerical, ... Type n numerical” and “Type 3 numerical, Type 4 numerical, ... Type n numerical”. When the first preset rule is “when the variable frequency is less than 20%, determine the corresponding target numerical data and / or target text numerical data as constants”, generate constants corresponding to the target text numerical data and target numerical data as “Type 1 numerical, Type 2 numerical, ... Type n numerical” and “Type 3 numerical, Type 4 numerical, ... Type n numerical” respectively. When the preset decision type is "Decision Type A", "Decision Type A" can correspond to multiple decision schemes "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n". For "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n", based on the aforementioned dynamic coefficient β and constants, where the constants can be numerical values ​​representing quantities or numerical values ​​representing variations, such as "Salary = 2000" and / or "Change of Permanent Address = 2", this invention does not impose any limitations. The calculation is performed according to the following formula, where "Category" corresponds to different target text numerical data and the target data type corresponding to the target numerical data:

[0132] Decision coefficient Σ = category * constant ∧ dynamic coefficient β

[0133] Finally, decision coefficients are obtained for multiple decision options: "Decision Coefficient 1 value, Decision Coefficient 2 value, Decision Coefficient 3 value, Decision Coefficient 4 value, ...". When the target timestamp is a "time unit in the sequential time series", the target timestamp is set as the X-axis of the third curve, and the decision coefficient Σ=(Category 1 * Constant ∧ Dynamic Coefficient β) + (Category 2 * Constant ∧ Dynamic Coefficient β) + ... is set as the Y-axis of the third curve, resulting in the third curve. The third curve is used to express the changes in the decision coefficients corresponding to "Decision Option 1, Decision Option 2, Decision Option 3, Decision Option 4... Decision Option n" under a time unit in the sequential time series.

[0134] In a specific implementation, embodiments of the present invention can determine target time data based on the third curve, and determine the corresponding target decision coefficient based on the target time data; for example, refer to Figure 4As shown, the "decision time point" on the X-axis is selected as the target time data. Based on the "decision time point", the corresponding decision coefficient n value on the Y-axis is determined. The "target decision coefficient 1" corresponding to the "decision coefficient 1 value", the "target decision coefficient 2" corresponding to the "decision coefficient 2 value", the "target decision coefficient 3" corresponding to the "decision coefficient 3 value", the "target decision coefficient 4" corresponding to the "decision coefficient 4 value", and so on, and the "target decision coefficient n" corresponding to the "decision coefficient n value" are obtained respectively.

[0135] In a specific implementation, the embodiments of the present invention can use the decision scheme corresponding to the target decision coefficient as the target decision scheme. For example, after obtaining the decision coefficients corresponding to "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n", the value of the decision coefficient n on the Y-axis is determined according to the "decision time point". The "target decision coefficient 1" corresponding to the "decision coefficient 1 value", the "target decision coefficient 2" corresponding to the "decision coefficient 2 value", the "target decision coefficient 3" corresponding to the "decision coefficient 3 value", the "target decision coefficient 4" corresponding to the "decision coefficient 4 value", and so on, and the "target decision coefficient n" corresponding to the "decision coefficient n value" are obtained respectively. By sorting the "target decision coefficients 1-n" in descending order, the order of the corresponding "decision coefficients 1-n values" can be determined, thereby further determining the order of the "decision schemes 1-n" corresponding to the "decision coefficients 1-n values". The first four are extracted, and the decision priority is determined in descending order as "decision scheme 3 > decision scheme 2 > decision scheme 1 > decision scheme 4". The decision scheme with the highest decision priority is selected as the target decision scheme.

[0136] Of course, the above examples are merely illustrative. Those skilled in the art can use other rules to determine the corresponding decision scheme through the target decision coefficient and thus select the target decision scheme. In this regard, the embodiments of the present invention do not impose any limitations.

[0137] This invention generates a third curve using multiple decision coefficients and a target timestamp. The third curve expresses the changes in decision coefficients corresponding to multiple decision schemes under a preset time sequence. Target time data is determined based on the third curve, and the corresponding target decision coefficient is determined based on the target time data. The decision scheme corresponding to the target decision coefficient is then used as the target decision scheme. This strengthens the dynamic correlation between different users and different categories of data. The decision coefficients allow for the sorting and selection of decision schemes based on time and value dimensions, further increasing the flexibility of data analysis. The timestamp-based approach imparts dynamism and continuity to the data, effectively supporting the relevance and accuracy of the data analysis results.

[0138] In an optional embodiment of the present invention, a first deviation magnitude value can be calculated for the target decision coefficient according to a first preset time period;

[0139] If the first deviation magnitude is less than the minimum threshold, the target decision scheme is deemed effective.

[0140] If the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold, then the second deviation magnitude value is calculated for the target decision coefficient according to the second preset time period;

[0141] If the first deviation value is greater than the highest threshold, the target decision scheme is determined to be invalid.

[0142] In practical applications, current data analysis methods cannot include textual information in the scope of analysis data and / or the relationships between analyzed data lack time dynamism and continuity. After analysis and decision-making, there is a lack of review of the effects and benefits of the decision, as well as insufficient basis for retrospective examination and optimization of the analysis methods and decision chain mapping relationships. Therefore, by converting different categories and forms of information into coefficients through calculation and evaluating these coefficients, the difficulty of reviewing decision analysis can be effectively reduced, and more accurate reference data can be provided.

[0143] In a specific implementation, embodiments of the present invention can calculate a first deviation magnitude value for the target decision coefficient according to a first preset time period. If the first deviation magnitude value is less than a minimum threshold, the target decision scheme is determined to be valid. If the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold, a second deviation magnitude value is calculated for the target decision coefficient according to a second preset time period. If the first deviation magnitude value is greater than the maximum threshold, the target decision scheme is determined to be invalid.For example, after obtaining the decision coefficients corresponding to "Decision Scheme 1, Decision Scheme 2, Decision Scheme 3, Decision Scheme 4... Decision Scheme n", the corresponding decision coefficient n value on the Y-axis is determined according to the "Decision Time Point". This yields the "Target Decision Coefficient 1" corresponding to "Decision Coefficient 1", the "Target Decision Coefficient 2" corresponding to "Decision Coefficient 2", the "Target Decision Coefficient 3" corresponding to "Decision Coefficient 3", the "Target Decision Coefficient 4" corresponding to "Decision Coefficient 4", and so on, until the "Target Decision Coefficient n" value is obtained. This process is then performed on the "Target Decision Coefficient 1-n". Sort in descending order to determine the ranking of the corresponding "decision coefficients 1-n values," thereby further determining the ranking of the "decision schemes 1-n" corresponding to the "decision coefficients 1-n values." Extract the first four values ​​and determine their decision priorities in descending order as "decision scheme 3 > decision scheme 2 > decision scheme 1 > decision scheme 4." Select the four decision schemes with the highest decision priorities as the target decision schemes. After implementing the schemes according to decision schemes 1-4, the first deviation value of the "target decision coefficients 1-4" can be calculated according to the first preset time period of "3-6 months." For example, after 3-6 months, the "target decision coefficients 1-4" will be... Coefficients 1 and 2 change from 1000 to 1300, target decision coefficient 3 changes from 1000 to 1500, and target decision coefficient 4 changes from 1000 to 1800. Taking the growth rate of target decision coefficients 1-n as the first deviation value, the first deviation value of target decision coefficients 1 and 2 is 30%, the first deviation value of target decision coefficient 3 is 50%, and the first deviation value of target decision coefficient 4 is 80%. If the minimum threshold is 40% and the maximum threshold is 70%, then the first deviation value of target decision coefficients 1 and 2 is less than the minimum threshold of 50%. If the deviation of "target decision coefficient 1, 2" is determined to be valid, and the deviation of "target decision coefficient 3" is higher than the minimum threshold of 50% but not higher than the maximum threshold of 70%, then the target decision coefficient 3 will be calculated according to the second preset time period of "6-12 months" to obtain the growth rate at that time as the second deviation value; if the first deviation of "target decision coefficient 4" is greater than the maximum threshold of 70%, then the target decision scheme 4 corresponding to the target decision coefficient 4 is determined to be invalid, and the decision scheme can be re-evaluated and calibrated in a comprehensive manner in terms of data source, analysis method, decision method, execution result and other dimensions.

[0144] In specific implementations, the minimum and maximum thresholds of this invention can be generated by preset methods.

[0145] This invention calculates a first deviation magnitude value for the target decision coefficient according to a first preset time period. If the first deviation magnitude value is less than a minimum threshold, the target decision scheme is deemed valid. If the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold, a second deviation magnitude value is calculated for the target decision coefficient according to a second preset time period. If the first deviation magnitude value is greater than the maximum threshold, the target decision scheme is deemed invalid. This enables post-decision review and analysis, allowing for the evaluation and optimization of the analysis method and decision chain.

[0146] To enable those skilled in the art to better understand the embodiments of the present invention, a complete example is used below to illustrate the embodiments of the present invention.

[0147] With the digital transformation of the hotel industry, large and medium-sized hotels and chain hotels have established their own membership systems to support their operations and development. Through online marketing and offline promotional activities, they are continuously expanding their membership base and accumulating vast amounts of member information. Hotels currently often use members as a target group of high-quality consumers for marketing analysis and provide them with exclusive and convenient digital experiences. Faced with massive amounts of data on hundreds of thousands or even millions of members, and exponentially increasing amounts of different types of information, choosing the right analytical methods to guide different decision-making processes is becoming an increasingly important focus for hotel management.

[0148] The main drawbacks of commonly used analytical methods are:

[0149] (1) The data source mainly consists of numerical data (such as the price of similar products, the quantity of similar products, actual sales, and various industry operating indicators), and does not include some textual information of members (such as address, job position, industry of employment, family members, etc.) in the analysis.

[0150] (2) The analysis method mainly compares the average actual operating value, threshold deviation and other general values ​​with the operating or industry index, and provides comparative scores through methods such as deviation degree and order of magnitude;

[0151] (3) After providing analysis and decision-making, there is a lack of review of the effects and benefits of post-decision evaluation, as well as the problem of reviewing and optimizing the analysis methods and decision chain mapping relationship, which limits the personalized and self-optimizing development of the hotel industry or customers in the process of use.

[0152] This invention updates data in the hotel membership system (such as member's basic information, family information, work information, and hotel consumption information) with each member's hotel consumption and personal changes. In particular, changes in members' circumstances and environments at different times lead to changes in their needs and preferences for hotel products. To meet the needs of the majority (70%-80%) of members (services, products, environment, location, price, etc.), hotels need to dynamically analyze member data for business decisions, assisting in achieving desired business goals at different times. Furthermore, retrospective analysis allows for verification of the analytical methods and decision-making effectiveness.

[0153] refer to Figure 5 , Figure 5 This is a flowchart illustrating the steps of another data analysis method provided in this embodiment of the invention. Exemplarily, this embodiment of the invention can perform data analysis through a complete system process of analysis and deduction, decision correlation, decision-making, review and evaluation, and optimization, with the following steps:

[0154] I. Analytical Methods

[0155] (1) Information Decoupling and Coupling: Based on hotel members' individual (gender, age, ethnicity, place of origin, travel itinerary), family (structure, number of people, address), work unit (industry, position, job title, income range), and behavioral trends (consumption type, amount, time, quantity, reviews) information, all data from the time the member information was created to the time of analysis is extracted and presented in a panoramic information matrix. Textual changes are decoupled and marked by variables and counted. For example, if a member's address changes, it changes from "0" to "1", and if it changes again, it changes to "α", "α = number of changes". Numerical changes are listed and marked by variables. This achieves the coupling of the member information array matrix, as shown below:

[0156]

[0157] (2) Multi-trajectory curve plotting and value determination of data variables: Based on the coupled array matrix, a two-dimensional planar curve is plotted, with the X-axis as the time axis and the Y-axis as the variable axis. From the single-person curve plot (reference) Figure 2 The constants and coefficients are determined by taking values ​​for variables with a frequency below 20%. For example, variables with a frequency below 20% are considered constants. Type coefficients are determined based on a multi-person plot (see reference). Figure 3 The intersection points and the number of intersection points above 70% constitute the value range. Based on the value range, the dynamic coefficient β is derived as follows: (high value * number of intersections + low value * number of intersections) / total number of intersections * total number of interval curves.

[0158] II. Decision-making methods

[0159] (1) Correlation between decision type and basic type: Based on different decision types, associate them with the corresponding basic types. (For example, when making a decision on the style of hotel renovation, the association can be based on the member's gender, age, travel history, family size, position, income, consumption type, amount, and evaluation; this method can be used to make different business decision directions in the hotel industry.)

[0160] (2) Analyze the correlation between data and the decision-making process: Through the analysis process, type values ​​can be obtained. The type constant is obtained by taking the type value variable frequency below 20%. The type dynamic coefficient β is derived by taking the value range of the intersection of multiple descriptions of type coefficients and the number of intersections above 70%. Based on these three types of values, the next step of rating and deduction is carried out by combining the correlation values ​​between decision type and basic type.

[0161] (3) Rating Deduction and Decision-Making: Trajectory curves are plotted based on the data types, constants, and dynamic coefficients associated with different business decision directions (see reference). Figure 4 The horizontal axis represents the time variable, and the vertical axis represents the decision coefficient Σ, where Σ = (Category 1 * constant ∧ dynamic coefficient β) + (Category 2 * constant ∧ dynamic coefficient β) + ..., thus forming a two-dimensional curve diagram with multiple decision types. This allows us to deduce the decision coefficient value of the decision direction within a certain time node or time interval, and sort the decision values ​​according to the time and value dimensions.

[0162] (4) Decision Review and Calibration: After implementation based on the decision ranking, a second-stage review of the business trend can be conducted at 3-6 months and 6-12 months. The member information data for 3-6 months can be extrapolated using the analysis and decision-making methods. If the deviation of the dynamic data in the analysis results is within 15%, it is considered a valid decision; within 15%-30%, it is considered a decision to proceed to the second-stage evaluation at 6-12 months; and if it exceeds 30%, it is considered a deviated decision. In this case, a comprehensive re-evaluation and calibration of the data source, analysis method, decision-making method, and execution results is required.

[0163] For example, using 20 sets of member data from a certain brand of hotel as a basis for hotel floor and room type configuration decisions:

[0164] 1. Acquire comprehensive member data and decouple and recouple member information;

[0165] 1.1 The individual member information arrays (20 groups) obtained through information decoupling and array-matrix coupling are shown in Table 3:

[0166] Table 3:

[0167]

[0168] 2. Plotting and assigning values ​​to multiple trajectory curves for individual and full data variables;

[0169] 2.1 The individual array matrix variables are depicted in a two-dimensional quadrant. Based on the obtained data of relevant types, the intersection points and the number of intersection points higher than 70% constitute the value interval. The type dynamic coefficient β is deduced based on the value interval. Where β = (high value * number of intersections + low value * number of intersections) / total number of intersections * total number of interval curves.

[0170] 2.2 The dynamic coefficient β obtained through step 2.1 is shown in Table 4:

[0171] Table 4:

[0172]

[0173]

[0174] 3. Deduction of the correlation between decision types and basic types;

[0175] 3.1 The room type and floor decision are correlated with the above 9 basic dynamic coefficients and deduced using the formula Σ=(Category 1 * constant ∧ dynamic coefficient β) + (Category 2 * constant ∧ dynamic coefficient β) + ...... The decision coefficients are obtained through this method, as shown in Table 5:

[0176] Table 5:

[0177]

[0178] 3.2 The results are plotted as a two-dimensional quadrant curve. The upper and lower limits are set by the intersection interval to form the decision result. The optimal room type decision corresponding to the floor with the best decision coefficient value is output, as shown in Table 6:

[0179] Table 6:

[0180]

[0181]

[0182] This invention aims to quantify all member data, establish a personal information quantification matrix, and reflect the values ​​in a two-dimensional quadrant to locate the intersection and threshold range of the member and type data, thereby deriving dynamic coefficients and generating decision coefficients, and providing sorting suggestions for review and decision-making at that time point. Furthermore, post-decision review and second-order inspection methods can be used for deductive review, allowing for the evaluation and optimization of analytical methods and decision chains. By decoupling and coupling member system information, member information is presented in a panoramic manner as an information numerical matrix for analysis. This information numerical matrix, through two-dimensional quadrant analysis, uses numerical curves to graphically analyze massive amounts of historical (hundreds of thousands, millions) of information from the member system. The text type variable "α", type dynamic coefficient "β", decision coefficient "Σ", and threshold value range in the deductive analysis process are all dynamic values ​​derived from actual data, possessing certain reference value within a specific decision cycle. In addition, post-decision review and second-order inspection methods provide a reference for optimizing subsequent analytical methods and decision chains. Through algorithms such as information array matrices and type data constants and variables, dynamic analysis and decision-making in hotel operations are achieved. Simultaneously, the review and deductive analysis allows for the examination and correction of methods and decision-making effects, improving the accuracy and scientific nature of dynamic analysis and decision-making data.

[0183] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0184] Reference Figure 6 The diagram shows a structural block diagram of a data analysis device provided in an embodiment of the present invention, which may specifically include the following modules:

[0185] The data acquisition module 601 is used to acquire text data and numerical data for multiple users;

[0186] The text numerical data generation module 602 is used to generate text numerical data by decoupling the text data;

[0187] The decision coefficient calculation module 603 is used to determine a preset decision type and calculate a decision coefficient for the preset decision type based on the text numerical data and the numerical data; the preset decision type has multiple corresponding decision schemes.

[0188] The target decision scheme determination module 604 is used to determine the target decision scheme from multiple decision schemes using the decision coefficients.

[0189] Optionally, the text data and the numerical data each have corresponding timestamps and data types; multiple users have one-to-one corresponding user identifiers, and the decision coefficient calculation module may include:

[0190] The array matrix generation submodule is used to couple the text numerical data and the numerical data based on the corresponding timestamp and data type to generate an array matrix for multiple users;

[0191] The association determination submodule is used to determine, from the array matrix, target text numerical data and target numerical data that are associated with the preset decision type according to the preset decision type; the target text numerical data and the target numerical data respectively have corresponding target timestamps and target data types;

[0192] The first curve generation submodule is used to generate a first curve using the target timestamp, the target text numerical data, and the target numerical data; the first curve is used to express the changes in target text numerical data and target numerical data corresponding to different target data types under a preset time sequence.

[0193] The second curve generation submodule is used to generate a second curve using the target timestamp, the user identifier, the target text numerical data, and the target numerical data; the second curve is used to express the changes in target text numerical data and target numerical data under the same target data type corresponding to different user identifiers under a preset time sequence.

[0194] The decision coefficient calculation submodule is used to calculate the decision coefficient for the preset decision type using the first curve and the second curve.

[0195] Optionally, the decision coefficient calculation submodule may include:

[0196] A constant value generation unit is used to calculate the target text numerical data and the frequency of variables corresponding to different timestamps based on the first curve, and generate constant values ​​based on the variable frequencies according to a first preset rule.

[0197] A curve number determination unit is used to determine the number of curves in the second curve based on the user identifier;

[0198] The curve intersection point determination unit is used to determine the curve intersection points for the second curve, and to determine the target number of intersection points from the curve intersection points according to a second preset rule;

[0199] The dynamic coefficient generation unit is used to calculate and generate dynamic coefficients based on the number of target intersection points and the number of curves;

[0200] The decision coefficient generation unit is used to generate decision coefficients for the preset decision type using the dynamic coefficients and the constant values.

[0201] Optionally, the target decision scheme determination module may include:

[0202] The third curve generation submodule is used to generate a third curve using multiple decision coefficients and the target timestamp; the third curve is used to express the changes in decision coefficients corresponding to multiple decision schemes under a preset time sequence;

[0203] The target decision coefficient determination submodule is used to determine the target time data based on the third curve and to determine the corresponding target decision coefficient based on the target time data.

[0204] The target decision scheme determination submodule is used to select the decision scheme corresponding to the target decision coefficient as the target decision scheme.

[0205] Optionally, it may also include:

[0206] The first deviation magnitude calculation submodule is used to calculate the first deviation magnitude value for the target decision coefficient according to a first preset time period.

[0207] The effective determination submodule is used to determine that the target decision scheme is effective if the first deviation amplitude value is less than the minimum threshold.

[0208] The second deviation magnitude calculation submodule is used to calculate the second deviation magnitude value for the target decision coefficient according to the second preset time period if the first deviation magnitude value is greater than or equal to the minimum threshold and less than or equal to the maximum threshold.

[0209] The invalidity determination submodule is used to determine that the target decision scheme is invalid if the first deviation magnitude value is greater than the highest threshold.

[0210] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0211] In addition, this invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described data analysis method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0212] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described data analysis method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0213] Figure 7 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0214] The electronic device 700 includes, but is not limited to, components such as: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, a processor 710, and a power supply 711. Those skilled in the art will understand that... Figure 7 The electronic device structures shown are not intended to limit the electronic device. An electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. In embodiments of the present invention, the electronic device includes, but is not limited to, mobile phones, tablet computers, laptops, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0215] It should be understood that, in this embodiment of the invention, the radio frequency unit 701 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 710; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 701 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the radio frequency unit 701 can also communicate with networks and other devices through a wireless communication system.

[0216] Electronic devices provide users with wireless broadband internet access through network module 702, such as helping users send and receive emails, browse web pages, and access streaming media.

[0217] The audio output unit 703 can convert audio data received by the radio frequency unit 701 or the network module 702 or stored in the memory 709 into audio signals and output them as sound. Furthermore, the audio output unit 703 can also provide audio output related to specific functions performed by the electronic device 700 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 703 includes a speaker, a buzzer, and a receiver, etc.

[0218] Input unit 704 is used to receive audio or video signals. Input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042. The GPU 7041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on display unit 706. The image frames processed by GPU 7041 can be stored in memory 709 (or other storage medium) or transmitted via radio frequency unit 701 or network module 702. Microphone 7042 can receive sound and process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via radio frequency unit 701 in telephone call mode.

[0219] The electronic device 700 also includes at least one sensor 705, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 7061 according to the ambient light level, and the proximity sensor can turn off the display panel 7061 and / or backlight when the electronic device 700 is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used to identify the posture of the electronic device (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. The sensor 705 may also include a fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be described in detail here.

[0220] The display unit 706 is used to display information input by the user or information provided to the user. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0221] User input unit 707 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of electronic devices. Specifically, user input unit 707 includes a touch panel 7071 and other input devices 7072. Touch panel 7071, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 7071). Touch panel 7071 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 710, which receives and executes commands from the processor 710. In addition, touch panel 7071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides touch panel 7071, user input unit 707 may also include other input devices 7072. Specifically, other input devices 7072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0222] Furthermore, the touch panel 7071 can cover the display panel 7061. When the touch panel 7071 detects a touch operation on or near it, it transmits the information to the processor 710 to determine the type of touch event. Subsequently, the processor 710 provides corresponding visual output on the display panel 7061 based on the type of touch event. Although in Figure 7 In this embodiment, the touch panel 7071 and the display panel 7061 are two independent components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 7071 and the display panel 7061 can be integrated to realize the input and output functions of the electronic device. The specific implementation is not limited here.

[0223] Interface unit 708 serves as an interface for connecting external devices to electronic device 700. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 708 can be used to receive input from external devices (e.g., data, power, etc.) and transmit the received input to one or more components within electronic device 700, or it can be used to transmit data between electronic device 700 and external devices.

[0224] The memory 709 can be used to store software programs and various data. The memory 709 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 709 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0225] The processor 710 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 709, and by calling data stored in the memory 709, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 710 may include one or more processing units; preferably, the processor 710 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 710.

[0226] The electronic device 700 may also include a power supply 711 (such as a battery) for supplying power to various components. Preferably, the power supply 711 is logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0227] In addition, the electronic device 700 includes some functional modules not shown, which will not be described in detail here.

[0228] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0229] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0230] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

[0231] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0232] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0233] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0234] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0235] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0236] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0237] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A data analysis method, characterized by, The method comprises the following steps: acquiring text data and numerical data of a plurality of users; generating text numerical data by decoupling the text data; determining a preset decision type, and calculating a decision coefficient for the preset decision type according to the text numerical data and the numerical data; the preset decision type has a plurality of decision schemes corresponding thereto; determining a target decision scheme from the plurality of decision schemes according to the decision coefficient; wherein the text data and the numerical data have corresponding time stamps and data types respectively; the plurality of users have one-to-one corresponding user identifiers; the step of calculating the decision coefficient for the preset decision type according to the text numerical data and the numerical data comprises the following steps: coupling the text numerical data and the numerical data based on the corresponding time stamps and data types to generate an array matrix for the plurality of users; determining target text numerical data and target numerical data having a correlation with the preset decision type from the array matrix according to the preset decision type; the target text numerical data and the target numerical data have corresponding target time stamps and target data types respectively; generating a first curve by the target time stamps, the target text numerical data and the target numerical data; the first curve is used to express the changes of the target text numerical data and the target numerical data corresponding to different target data types under a preset time sequence; generating a second curve by the target time stamps, the user identifiers, the target text numerical data and the target numerical data; the second curve is used to express the changes of the target text numerical data and the target numerical data of the same target data type corresponding to different user identifiers under a preset time sequence; calculating the variable frequency of the target text numerical data and the target numerical data corresponding to different time stamps according to the first curve, and generating a constant numerical value based on the variable frequency according to a first preset rule; determining the number of curves in the second curve based on the user identifiers; determining the curve intersection points of the second curve, and determining the target intersection point number from the curve intersection points according to a second preset rule; calculating based on the target intersection point number and the number of curves to generate a dynamic coefficient; generating the decision coefficient for the preset decision type by the dynamic coefficient and the constant numerical value.

2. The method of claim 1, wherein, The step of determining the target decision scheme from the plurality of decision schemes according to the decision coefficient comprises the following steps: generating a third curve by the plurality of decision coefficients and the target time stamps; the third curve is used to express the changes of the decision coefficients corresponding to the plurality of decision schemes under a preset time sequence; determining target time data according to the third curve, and determining the corresponding target decision coefficient according to the target time data; taking the decision scheme corresponding to the target decision coefficient as the target decision scheme.

3. The method of claim 2, wherein, The method further comprises the following steps: calculating a first deviation amplitude value for the target decision coefficient according to a first preset time period; if the first deviation amplitude value is less than a minimum threshold value, determining that the target decision scheme is valid. If the first deviation amplitude value is greater than or equal to the minimum threshold value and less than or equal to the maximum threshold value, a second deviation amplitude value is calculated for the target decision coefficient according to a second preset time period; If the first deviation amplitude value is greater than the maximum threshold value, it is determined that the target decision scheme is invalid.

4. A data analysis device, characterized by, Comprise: A data acquisition module for acquiring text data and numerical data for a plurality of users; A text numerical data generation module for generating text numerical data by decoupling the text data; A decision coefficient calculation module for determining a preset decision type and calculating a decision coefficient for the preset decision type according to the text numerical data and the numerical data; the preset decision type has a plurality of corresponding decision schemes; A target decision scheme determination module for determining a target decision scheme from a plurality of decision schemes through the decision coefficient; Wherein, the text data and the numerical data have corresponding time stamps and data types respectively; a plurality of users have one-to-one user identification, and the decision coefficient calculation module comprises: An array matrix generation submodule for coupling the text numerical data and the numerical data based on the corresponding time stamps and data types to generate an array matrix for a plurality of users; An association relationship determination submodule for determining target text numerical data and target numerical data having an association relationship with the preset decision type from the array matrix according to the preset decision type; the target text numerical data and the target numerical data have corresponding target time stamps and target data types respectively; A first curve generation submodule for generating a first curve through the target time stamp, the target text numerical data and the target numerical data; the first curve is used to express the changes of the target text numerical data and the target numerical data corresponding to different target data types under a preset time sequence; A second curve generation submodule for generating a second curve through the target time stamp, the user identification, the target text numerical data and the target numerical data; the second curve is used to express the changes of the target text numerical data and the target numerical data of the same target data type corresponding to different user identifications under a preset time sequence; A constant value generation unit for calculating the variable frequency of the target text numerical data and the target numerical data corresponding to different time stamps according to the first curve, and generating a constant value based on the variable frequency according to a first preset rule; A curve number determination unit for determining the number of curves in the second curve based on the user identification; A curve intersection determination unit for determining the curve intersection points of the second curve and determining the target intersection point number from the curve intersection points according to a second preset rule; A dynamic coefficient generation unit for calculating based on the target intersection point number and the number of curves to generate a dynamic coefficient; A decision coefficient generation unit for generating a decision coefficient for the preset decision type through the dynamic coefficient and the constant value.

5. The apparatus of claim 4, wherein, The target decision scheme determination module comprises: a third curve generating submodule configured to generate a third curve based on the plurality of decision coefficients and the target timestamp, the third curve being configured to express the variation of the decision coefficients corresponding to the plurality of decision schemes under a preset timing; a target decision coefficient determining submodule configured to determine target time data based on the third curve, and determine a target decision coefficient corresponding to the target time data; a target decision scheme determining submodule configured to determine a decision scheme corresponding to the target decision coefficient as a target decision scheme.

6. The apparatus of claim 5, wherein, Further comprising: a first deviation amplitude value calculating submodule configured to calculate a first deviation amplitude value for the target decision coefficient according to a first preset time period; an effective determining submodule configured to determine that the target decision scheme is effective if the first deviation amplitude value is less than a minimum threshold value; a second deviation amplitude value calculating submodule configured to calculate a second deviation amplitude value for the target decision coefficient according to a second preset time period if the first deviation amplitude value is greater than or equal to the minimum threshold value and less than or equal to a maximum threshold value; an ineffective determining submodule configured to determine that the target decision scheme is ineffective if the first deviation amplitude value is greater than the maximum threshold value.

7. An electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus; the memory is configured to store a computer program; the processor is configured to execute the program stored on the memory, and implement the method in any one of claims 1-3.

8. A computer readable storage medium having instructions stored thereon, which when executed by one or more processors, cause the processors to perform the method in any one of claims 1-3.

Images