A travel approval adaptive processing method and system

Abstract

This invention discloses an adaptive processing method and system for business travel approval, belonging to the technical field of enterprise information management. The method includes: receiving business travel application data initiated by an applicant; obtaining a historical business travel dataset corresponding to the applicant and calculating the applicant's credit score based on the historical business travel dataset; extracting travel features from the business travel application data and calculating a travel risk score based on the travel features; dynamically selecting a target business travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score; and executing the approval process for the business travel application data according to the target business travel approval path. This achieves a balance between approval efficiency and risk control, significantly improving the flexibility, adaptability, and intelligence level of business travel approval.

Description

Technical Field

[0001] This invention relates to the field of enterprise information management technology, and in particular to an adaptive processing method and system for business travel approval. Background Technology

[0002] Existing travel approval methods suffer from the following technical shortcomings: First, the approval process is rigid, failing to dynamically adjust approval strategies based on the applicant's historical credit history and the risk characteristics of the specific itinerary. Even employees with good credit still face cumbersome approval steps, leading to low efficiency and impacting business response speed. Second, high-risk itineraries cannot be effectively identified and prioritized for review, potentially causing compliance risks and financial losses for the company. Third, the approval path is completely fixed, lacking a mechanism to dynamically select different approval templates based on the applicant and itinerary characteristics, thus failing to achieve an adaptive balance between efficiency and risk.

[0003] Therefore, there is an urgent need for an adaptive processing technology for travel approval that can integrate applicant credit assessment and travel risk prediction to solve the technical problems of rigid approval processes and lack of dynamic adaptability in existing technologies. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides an adaptive processing method and system for travel approval, aiming to solve the technical problems of rigid approval processes and lack of dynamic adaptability in the prior art.

[0005] This invention provides an adaptive processing method for travel approval, comprising: Receive travel application data initiated by applicants; Obtain the applicant's historical travel history as a dataset, and calculate the applicant's credit score based on the historical travel history dataset; Extract the itinerary features from the travel application data, and calculate the itinerary risk score based on the itinerary features; Based on the credit score and the trip risk score, a target travel approval path is dynamically selected from multiple predefined approval path templates; The approval process for the travel application data is executed according to the target travel approval path.

[0006] In some embodiments, obtaining the applicant's historical travel history as a dataset and calculating the applicant's credit score based on the historical travel history dataset includes: Obtain the applicant's historical travel history as a dataset, wherein the historical travel history dataset includes the applicant's most recent travel history before the current time. The single behavior scoring sequence corresponding to each business travel application ; According to the time decay weight formula Assign weights to each historical travel application, among which , For the current time, For the first The time when the travel application was submitted. The preset decay coefficient is used to control the rate at which the influence of historical behavior decays over time. The posterior credit status parameters are calculated using the Bayesian smoothing formula. : ; In the formula, These are prior weights, used to control the strength of prior information in the group; The prior mean of group credit; The posterior credit status parameters are mapped to the 0-100 range using a normalization function to obtain the credit score. : ; In the formula, and These are the baseline mean and baseline standard deviation of the group credit status distribution, respectively.

[0007] In some embodiments, the single behavior score It is calculated using the following formula: ; In the formula, For a binary variable, when the first... The value is 1 if the travel application is approved on the first attempt, and 0 otherwise. This represents a negative mapping of the degree of cost exceeding the limit, where For the first The actual cost of this business trip. The corresponding standard fee; This indicates the penalty for the number of itinerary changes, among which... For the first Number of itinerary changes for this business trip; , indicating penalties for approval delays, among which For the first The approval process for this business trip took a long time. This represents the average approval time of the system. , , , , These are preset positive weighting coefficients, used to control the degree of influence of each behavioral indicator on a single behavioral score.

[0008] In some embodiments, extracting travel features from the travel application data and calculating a travel risk score based on the travel features includes: Extract multiple raw values ​​of itinerary features from the travel application data. ; For each trip feature, the corresponding risk factor is calculated using the logistic membership function. : ; in, The preset slope parameter, To set a preset risk prominence threshold, ; By fusing the various risk factors using a multiplicative risk probability model, a joint risk probability is obtained. : ; The system detects whether the travel features contain a preset high-risk combination; if so, it calculates a cross-enhancement term. ,in For the first The enhancement coefficient of the combination, For indicator functions, when the first The value is 1 when a high-risk combination occurs, and 0 otherwise. Calculate the trip risk score : .

[0009] In some embodiments, dynamically selecting a target travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score includes: Based on the type identifier of the travel application data, a target two-dimensional decision matrix is ​​determined from a plurality of preset two-dimensional decision matrices; wherein, the plurality of preset two-dimensional decision matrices correspond to different types of travel applications, and each two-dimensional decision matrix has an independent credit score interval division, itinerary risk score interval division, and mapping relationship between decision area and approval path template; The credit score and travel risk score are mapped to the target two-dimensional decision matrix to determine the target decision region in the target two-dimensional decision matrix; Based on the target decision area, select the corresponding target approval path template from multiple predefined approval path templates to determine the target travel approval path.

[0010] In some embodiments, it also includes: After receiving the travel application data, the integrity of the travel application data is checked; the integrity check includes: detecting whether the travel application data is missing any preset required fields; In response to the detection of any missing required field, a missing field prompt message is generated and returned to the application end until the complete travel application data is received.

[0011] In some embodiments, it also includes: Obtain the preset approval time limit of the current approval node in the target travel approval path; Start a timer to monitor the actual time consumed by the current approval node; When the actual time consumed exceeds the preset approval time limit and no approval result is received, an overdue reminder message is automatically sent to the approver at the current approval node; If no approval result is received within the preset waiting time after the timeout reminder message is sent, the travel application data will be automatically transferred to the backup approver of the current approval node, and the current approval node in the target travel approval path will be updated to the backup approver node.

[0012] In some embodiments, it also includes: After generating the target travel approval path, the budget pool identifier associated with each approval node is queried based on the set of approval nodes of the target travel approval path. Based on the estimated cost information of the travel application data, the corresponding budget amount is pre-deducted from the budget pool corresponding to the budget pool identifier to generate a budget pre-occupancy record; If the approval result is rejected at any point in the approval process, the budget pre-allocation record will be released and the pre-deducted budget amount will be returned to the corresponding budget pool. If the entire approval process is completed, the budget pre-allocation record will be converted into an actual budget deduction record.

[0013] In some embodiments, it also includes: Before receiving the travel application data, obtain partial application information that has been entered by the applicant, which includes at least the applicant's identity and travel destination; Based on the applicant's identity and the travel destination, retrieve historical travel application records that are the same as or similar to the travel destination from the historical travel database; Extract itinerary data fields from retrieved historical travel application records; The extracted itinerary data fields are used as recommended options to generate a populate suggestion list and push it to the application end; In response to receiving a confirmation instruction from the application client for any of the recommended options in the suggestion list, the corresponding itinerary data field value is automatically filled into the corresponding field position of the travel application data; After the data is filled in, receive the complete travel request data.

[0014] This invention provides an adaptive processing system for business travel approval, comprising: The receiving module is used to receive travel application data initiated by the applicant; The credit scoring module is used to obtain the applicant's historical travel data set and calculate the applicant's credit score based on the historical travel data set. The risk scoring module is used to extract the itinerary features from the travel application data and calculate the itinerary risk score based on the itinerary features; The selection module is used to dynamically select a target travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score. The execution module is used to execute the approval process of the travel application data according to the target travel approval path.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By introducing credit scoring and travel risk scoring mechanisms, an adaptive quantitative assessment of the applicant's credit and travel risk is achieved. By dynamically selecting approval path templates, the approval process can be dynamically adjusted according to the applicant's credit and travel risk, achieving a balance between approval efficiency and risk control, and significantly improving the flexibility, adaptability and intelligence of travel approval. Attached Figure Description

[0016] The embodiments of the present invention will be further described below with reference to the accompanying drawings: Figure 1 This is a schematic diagram illustrating the implementation process of an adaptive processing method for travel approval provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an adaptive processing system for business travel approval provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0019] If the application documents contain similar descriptions such as "first, second, third", the following explanation shall be added: In the following description, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0021] To address the problems existing in related technologies, this invention provides an adaptive processing method for travel approval, wherein the executing entity of this method can be an electronic device. The electronic device can be various types of terminals such as laptops, tablets, desktop computers, set-top boxes, and mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), or it can be implemented as a server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0022] In some embodiments, the functions implemented by the processing method provided in this invention can be achieved by the processor of an electronic device calling program code, wherein the program code can be stored in a computer storage medium.

[0023] This invention provides an adaptive processing method for travel approval. Figure 1 This is a schematic diagram illustrating the implementation flow of an adaptive processing method for travel approval provided in an embodiment of the present invention, as shown below. Figure 1 As shown, it includes: Step S1: Receive travel application data initiated by the applicant; In this embodiment of the invention, the travel application data is filled in and submitted by the applicant on the application platform, including but not limited to the applicant's identity information, travel destination, departure time, return time, preferred mode of transportation, accommodation standard, estimated cost, reason for business trip, and accompanying persons. The application platform can be a web page, a mobile application, or the interface of an enterprise's internal travel management system.

[0024] Step S2: Obtain the applicant's historical travel data set, and calculate the applicant's credit score based on the historical travel data set; In some embodiments, step S2 includes: Step S21: Obtain the applicant's historical travel data set, wherein the historical travel data set includes the applicant's most recent travel history before the current time. The single behavior scoring sequence corresponding to each business travel application ; Step S22: According to the time decay weight formula Assign weights to each historical travel application, among which , For the current time, For the first The time when the travel application was submitted. The preset decay coefficient is used to control the rate at which the influence of historical behavior decays over time. Step S23: Calculate the posterior credit status parameters using the Bayesian smoothing formula. : ; In the formula, These are prior weights, used to control the strength of prior information in the group; The prior mean of group credit; Step S24: Map the posterior credit status parameters to the 0-100 range using a normalization function to obtain the credit score. : ; In the formula, and These are the baseline mean and baseline standard deviation of the group credit status distribution, respectively.

[0025] In this embodiment of the invention, recent behavior reflects current creditworthiness better than long-term behavior. An exponential decay weighting is employed. This makes the influence of actions taken more recent than those taken more recent. However, for new employees with a small sample size, simply using historical data can be unstable; therefore, Bayesian smoothing is introduced: using the group's prior mean... As a priori beliefs, through priori weights Balance individual and group data to avoid overfitting with small samples. Finally, through... The function maps the posterior parameters to a score of 0-100, giving the score an intuitive percentage meaning.

[0026] In some embodiments, the single behavior score It is calculated using the following formula: ; In the formula, For a binary variable, when the first... The value is 1 if the travel application is approved on the first attempt, and 0 otherwise. This represents a negative mapping of the degree of cost exceeding the limit, where For the first The actual cost of this business trip. The corresponding standard fee; This indicates the penalty for the number of itinerary changes, among which... For the first Number of itinerary changes for this business trip; , indicating penalties for approval delays, among which For the first The approval process for this business trip took a long time. This represents the average approval time of the system. , , , , These are preset positive weighting coefficients, used to control the degree of influence of each behavioral indicator on a single behavioral score.

[0027] In this embodiment of the invention, the contribution of a single business trip to credit is not a simple summation, but rather involves nonlinearity and interaction effects. For example, exceeding the expense limit is inherently a negative behavior, but if it is accompanied by approval delays, the negative impact will be amplified. Interaction terms are introduced. This is to capture the synergistic negative impact between cost overruns and approval delays; that is, the simultaneous presence of both cost overruns and approval delays is more severe than either problem alone. Hyperbolic tangent function Map the output value to The interval has good saturation characteristics, avoiding excessive influence of extreme values ​​on the score.

[0028] Step S3: Extract the itinerary features from the travel application data and calculate the itinerary risk score based on the itinerary features; In some embodiments, step S3 includes: Step S31: Extract multiple raw values ​​of itinerary features from the travel application data. ; Step S32: For each trip feature, calculate the corresponding risk factor using the logistic membership function. : ; in, The preset slope parameter, To set a preset risk prominence threshold, ; Step S33: Fuse the various risk factors using a multiplicative risk probability model to obtain the joint risk probability. : ; Step S34: Detect whether the travel features contain a preset high-risk combination. If so, calculate the cross-enhancement term. ,in For the first The enhancement coefficient of the combination, For indicator functions, when the first The value is 1 when a high-risk combination occurs, and 0 otherwise. Step S35: Calculate the trip risk score : .

[0029] In this embodiment of the invention, the itinerary features include: destination risk level: a risk level value determined based on factors such as the safety status of the destination, epidemic risk, and political stability; cost deviation: the ratio of estimated cost to standard cost; itinerary complexity: the number of transfers, transits, etc.; time anomaly: whether the travel time is during holidays, early morning hours, or other irregular times; accommodation standard deviation: the degree of deviation between the requested accommodation standard and the standard corresponding to the job level; and application lead time: the number of days between the application submission time and the planned departure time. Traditional methods linearly weight risk features, but real-world risks are often multiplicative: when multiple low-probability risk factors coexist, the overall risk increases exponentially. Furthermore, certain combinations of features can generate additional synergistic risks; therefore, cross-enhancement terms are introduced. (High-risk combinations are identified through an indicator function). Finally, each feature is mapped to a risk probability using a logistic function, resulting in a smoother transition than hard thresholding. This approach better reflects the non-linear superposition characteristics of risk compared to linear weighting.

[0030] Step S4: Based on the credit score and the trip risk score, dynamically select the target travel approval path from multiple predefined approval path templates; In some embodiments, step S4 includes: Step S41: Based on the type identifier of the travel application data, determine a target two-dimensional decision matrix from a set of preset two-dimensional decision matrices; wherein, the preset two-dimensional decision matrices correspond to different types of travel applications, and each two-dimensional decision matrix has an independent credit scoring interval division, itinerary risk scoring interval division, and mapping relationship between the decision area and the approval path template; Step S42: Map the credit score and the trip risk score to the target two-dimensional decision matrix to determine the target decision region where the credit score and the trip risk score are located in the target two-dimensional decision matrix; Step S43: Based on the target decision area, select the corresponding target approval path template from multiple predefined approval path templates to determine the target travel approval path.

[0031] In this embodiment of the invention, the system pre-sets multiple two-dimensional decision matrices, each corresponding to a type of travel application. Different types of travel applications have different risk characteristics and approval requirements, thus requiring independent decision matrix configurations. The structure of each two-dimensional decision matrix is ​​as follows: the horizontal axis represents the credit scoring range, and the vertical axis represents the trip risk scoring range. The matrix is ​​divided into multiple decision regions, each corresponding to an approval path template. The approval path template defines the node sequence of the approval process, the approver at each node, the approval authority, and the approval time limit. Taking a certain type of decision matrix as an example: Region A: Credit score ≥ 80 and risk score < 30, corresponding to the simplified path; Region B: Credit score ≥ 80 and 30 ≤ risk score < 70, corresponding to the simplified path; Region C: Credit score ≥ 80 and 70 ≤ risk score, corresponding to the standard path; Region D: 50 ≤ credit score < 80 and risk score < 30, corresponding to the simplified path; Region E: 50 ≤ credit score < 80 and 30 ≤ risk score < 70, corresponding to the standard path; Region F: 50 ≤ credit score < 80 and 70 ≤ risk score, corresponding to the enhanced path; Region G: Credit score < 50 and risk score < 70, corresponding to the simplified path; Region B: Credit score < 80 and 30 ≤ risk score < 70, corresponding to the simplified path; Region C: Credit score ≥ 80 and 70 ≤ risk score, corresponding to the standard path; Region D: 50 ≤ credit score < 80 and risk score < 30, corresponding to the simplified path; Region E: 50 ≤ credit score < 80 and 30 ≤ risk score < 70, corresponding to the standard path; Region F: 50 ≤ credit score < 80 and 70 ≤ risk score, corresponding to the enhanced path; Region G: Credit score < 50 and risk score < 70, corresponding to the enhanced path; Region G: Credit score < 50 and risk score < 70, corresponding to the simplified path; Region B: Credit score < 80 and 30 ≤ risk score < 70, corresponding to the simplified path; Region C: Credit score ≥ 80 and 30 ≤ risk score < 70, corresponding to the enhanced path; Region D: Credit score < 80 and 30 ≤ risk score < 30, corresponding to the simplified path; Region E: Credit score < 80 and 30 ≤ risk score < 70, corresponding to the standard path; Region F: Credit score < For regions H and I, where the credit score is less than 30 and the risk score is less than 70, the corresponding path is the standard path. Region H has a credit score less than 50 and a risk score of 30 ≤ risk score, corresponding to the enhanced path. Region I has a credit score less than 50 and a risk score of 70 ≤ risk score, corresponding to the complete path. The paths are as follows: Minimal Path: No manual approval required, automatic system approval, with random checks afterward; Simplified Path: Only one level of approval from the direct supervisor; Standard Path: Two levels of approval from the direct supervisor and department head; Enhanced Path: Three levels of approval from the direct supervisor, department head, and financial auditor; Complete Path: Four levels of approval from the direct supervisor, department head, financial auditor, and supervising supervisor, requiring additional supporting documentation. Based on the type identifier of the travel application data, a target two-dimensional decision matrix is ​​determined. The calculated credit score and travel risk score are mapped into this matrix to determine the target decision region, and then the corresponding target approval path template is selected to determine the target travel approval path.

[0032] Step S5: Execute the approval process for the travel application data according to the target travel approval path.

[0033] In this embodiment of the invention, travel application data is sequentially transferred to each approval node according to the determined target travel approval path. Upon receiving the approval notification, the approver at each node reviews the application data and makes an approval decision to approve, reject, or return for modification. The system records the approval results and opinions at each node until the process ends or terminates. This achieves a balance between approval efficiency and risk control, significantly improving the flexibility, adaptability, and intelligence of travel approval.

[0034] In some embodiments, it also includes: After receiving the travel application data, the integrity of the travel application data is checked; the integrity check includes: detecting whether the travel application data is missing any preset required fields; In response to the detection of any missing required field, a missing field prompt message is generated and returned to the application end until the complete travel application data is received.

[0035] After receiving the travel application data, the system performs a completeness check. This check includes detecting whether any pre-defined mandatory fields are missing (such as applicant identification, travel destination, departure time, estimated cost, and reason for travel). If any mandatory field is detected as missing, the system generates a missing field prompt and returns it to the applicant, instructing them to complete the field. Only after receiving the completed travel application data does the system proceed to the subsequent credit scoring and risk scoring calculation processes. This mechanism ensures the quality of data entering the approval process and reduces approval rejections and process blockages caused by incomplete information. For example, if an applicant's application lacks the "estimated cost" field, the system immediately returns a prompt "Please fill in the estimated cost," highlights the field on the applicant's end, and the applicant completes and resubmits the application. Only after the system verifies the data again does it proceed to the next step.

[0036] In some embodiments, it also includes: Obtain the preset approval time limit of the current approval node in the target travel approval path; Start a timer to monitor the actual time consumed by the current approval node; When the actual time consumed exceeds the preset approval time limit and no approval result is received, an overdue reminder message is automatically sent to the approver at the current approval node; If no approval result is received within the preset waiting time after the timeout reminder message is sent, the travel application data will be automatically transferred to the backup approver of the current approval node, and the current approval node in the target travel approval path will be updated to the backup approver node.

[0037] In this embodiment of the invention, the system obtains the preset approval time limit of the current approval node in the target travel approval path. A timer is started to monitor the actual time spent at the current approval node in real time. The timer can be implemented using a scheduled task or an event-driven approach, recording the timestamp of the application data entering the current node and calculating the difference with the current time. When the actual time spent exceeds the preset approval time limit and no approval result is received, the system automatically sends a timeout reminder message (such as system in-app message, email, SMS, WeChat, etc.) to the approver of the current approval node. The timeout reminder message includes information such as the application number, applicant's name, travel destination, and waiting time, so that the approver can quickly locate and process the application. If no approval result is received within the preset waiting time after sending the timeout reminder message, the system automatically transfers the travel application data to the backup approver of the current approval node (such as the approver's superior or other responsible persons in the same department) and updates the current approval node in the target travel approval path to the backup approver node. The information of the backup approver is pre-configured in the organizational structure database; for example, the backup approver of the direct supervisor is the department head, and the backup approver of the department head is the supervising leader. This mechanism effectively avoids prolonged process blockages caused by approvers being on business trips, on vacation, resigning, or negligent, thus ensuring approval efficiency.

[0038] In some embodiments, it also includes: After generating the target travel approval path, the budget pool identifier associated with each approval node is queried based on the set of approval nodes of the target travel approval path. Based on the estimated cost information of the travel application data, the corresponding budget amount is pre-deducted from the budget pool corresponding to the budget pool identifier to generate a budget pre-occupancy record; If the approval result is rejected at any point in the approval process, the budget pre-allocation record will be released and the pre-deducted budget amount will be returned to the corresponding budget pool. If the entire approval process is completed, the budget pre-allocation record will be converted into an actual budget deduction record.

[0039] In this embodiment of the invention, after generating the target travel approval path, the system queries the budget pool identifier associated with each approval node based on the set of approval nodes in the target travel approval path. Different approval nodes may correspond to different budget management permissions and budget pools. For example, the direct supervisor node is associated with the department's daily operation budget pool, the department head node is associated with the department's annual travel budget pool, and the financial audit node is associated with the company's unified travel budget pool. Based on the estimated cost information of the travel application data, the system pre-deducts the corresponding budget amount from the budget pool corresponding to the budget pool identifier, generating a budget pre-allocation record. The budget pre-allocation record records the pre-deducted budget amount, budget pool identifier, pre-allocation time, application number, and other information. The pre-deduction operation adopts a database transaction mechanism to ensure the accuracy and consistency of the budget pool balance. If the approval result at any node during the approval process is a rejection, the system automatically releases the budget pre-allocation record, returns the pre-deducted budget amount to the corresponding budget pool, and makes that portion of the budget available again. The release operation also adopts a transaction mechanism and is executed synchronously with the update of the approval result status. If the entire approval process is successful, the pre-allocated budget record will be converted into an actual budget deduction record, and the corresponding amount will be officially deducted from the corresponding budget pool. The conversion operation is triggered when the last approval node is passed, updating the budget pool balance and generating financial vouchers. This mechanism enables real-time linkage between the approval process and budget management, avoiding duplicate budget allocation and management lag.

[0040] In some embodiments, it also includes: Before receiving the travel application data, obtain partial application information that has been entered by the applicant, which includes at least the applicant's identity and travel destination; Based on the applicant's identity and the travel destination, retrieve historical travel application records that are the same as or similar to the travel destination from the historical travel database; Extract itinerary data fields from retrieved historical travel application records; The extracted itinerary data fields are used as recommended options to generate a populate suggestion list and push it to the application end; In response to receiving a confirmation instruction from the application client for any of the recommended options in the suggestion list, the corresponding itinerary data field value is automatically filled into the corresponding field position of the travel application data; After the data is filled in, receive the complete travel request data.

[0041] In this embodiment of the invention, before receiving complete travel application data, the system obtains partial application information already entered by the applicant, including at least the applicant's identity and travel destination. Based on the applicant's identity and travel destination, the system retrieves historical travel application records with the same or similar destinations from the historical travel database. Frequently occurring itinerary data fields (such as frequently used hotel names, preferred modes of transportation, standard cost ranges, and common reasons for business trips) are extracted from the historical records and used as suggested options to generate a suggested list, which is then pushed to the applicant. The suggested options are sorted by frequency of occurrence, with the most frequent option listed first. The applicant can select a suggested option from the list for one-click confirmation, and the system automatically fills the corresponding itinerary data field values ​​into the corresponding field positions in the travel application data. This function significantly reduces the applicant's repetitive data entry workload and improves efficiency and accuracy.

[0042] Based on the foregoing embodiments, this invention provides an adaptive processing system for travel approval. The modules and units included in the system can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0043] This invention provides an adaptive processing system for business travel approval. Figure 2 This is a schematic diagram of the structure of an adaptive processing system for business travel approval provided in an embodiment of the present invention, as shown below. Figure 2 As shown, it includes: The receiving module is used to receive travel application data initiated by the applicant; The credit scoring module is used to obtain the applicant's historical travel data set and calculate the applicant's credit score based on the historical travel data set. The risk scoring module is used to extract the itinerary features from the travel application data and calculate the itinerary risk score based on the itinerary features; The selection module is used to dynamically select a target travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score. The execution module is used to execute the approval process of the travel application data according to the target travel approval path.

[0044] In some embodiments, the credit scoring module is further configured to: Obtain the applicant's historical travel history as a dataset, wherein the historical travel history dataset includes the applicant's most recent travel history before the current time. The single behavior scoring sequence corresponding to each business travel application ; According to the time decay weight formula Assign weights to each historical travel application, among which , For the current time, For the first The time when the travel application was submitted. The preset decay coefficient is used to control the rate at which the influence of historical behavior decays over time. The posterior credit status parameters are calculated using the Bayesian smoothing formula. : ; In the formula, These are prior weights, used to control the strength of prior information in the group; The prior mean of group credit; The posterior credit status parameters are mapped to the 0-100 range using a normalization function to obtain the credit score. : ; In the formula, and These are the baseline mean and baseline standard deviation of the group credit status distribution, respectively.

[0045] In some embodiments, the credit scoring module is further configured to calculate a single behavior score as follows: ; In the formula, For a binary variable, when the first... The value is 1 if the travel application is approved on the first attempt, and 0 otherwise. This represents a negative mapping of the degree of cost exceeding the limit, where For the first The actual cost of this business trip. The corresponding standard fee; This indicates the penalty for the number of itinerary changes, among which... For the first Number of itinerary changes for this business trip; , indicating penalties for approval delays, among which For the first The approval process for this business trip took a long time. This represents the average approval time of the system. , , , , These are preset positive weighting coefficients, used to control the degree of influence of each behavioral indicator on a single behavioral score.

[0046] In some embodiments, the risk scoring module is further configured to: Extract multiple raw values ​​of itinerary features from the travel application data. ; For each trip feature, the corresponding risk factor is calculated using the logistic membership function. : ; in, The preset slope parameter, To set a preset risk prominence threshold, ; By fusing the various risk factors using a multiplicative risk probability model, a joint risk probability is obtained. : ; The system detects whether the travel features contain a preset high-risk combination; if so, it calculates a cross-enhancement term. ,in For the first The enhancement coefficient of the combination, For indicator functions, when the first The value is 1 when a high-risk combination occurs, and 0 otherwise. Calculate the trip risk score : .

[0047] In some embodiments, the selection module is further configured to: Based on the type identifier of the travel application data, a target two-dimensional decision matrix is ​​determined from a plurality of preset two-dimensional decision matrices; wherein, the plurality of preset two-dimensional decision matrices correspond to different types of travel applications, and each two-dimensional decision matrix has an independent credit score interval division, itinerary risk score interval division, and mapping relationship between decision area and approval path template; The credit score and travel risk score are mapped to the target two-dimensional decision matrix to determine the target decision region in the target two-dimensional decision matrix; Based on the target decision area, select the corresponding target approval path template from multiple predefined approval path templates to determine the target travel approval path.

[0048] In some embodiments, an integrity verification module is also included: After receiving the travel application data, the integrity of the travel application data is checked; the integrity check includes: detecting whether the travel application data is missing any preset required fields; In response to the detection of any missing required field, a missing field prompt message is generated and returned to the application end until the complete travel application data is received.

[0049] In some embodiments, a timeout processing module is also included: Obtain the preset approval time limit of the current approval node in the target travel approval path; Start a timer to monitor the actual time consumed by the current approval node; When the actual time consumed exceeds the preset approval time limit and no approval result is received, an overdue reminder message is automatically sent to the approver at the current approval node; If no approval result is received within the preset waiting time after the timeout reminder message is sent, the travel application data will be automatically transferred to the backup approver of the current approval node, and the current approval node in the target travel approval path will be updated to the backup approver node.

[0050] In some embodiments, a budget linkage module is also included: After generating the target travel approval path, the budget pool identifier associated with each approval node is queried based on the set of approval nodes of the target travel approval path. Based on the estimated cost information of the travel application data, the corresponding budget amount is pre-deducted from the budget pool corresponding to the budget pool identifier to generate a budget pre-occupancy record; If the approval result is rejected at any point in the approval process, the budget pre-allocation record will be released and the pre-deducted budget amount will be returned to the corresponding budget pool. If the entire approval process is completed, the budget pre-allocation record will be converted into an actual budget deduction record.

[0051] In some embodiments, an intelligent recommendation module is also included: Before receiving the travel application data, obtain partial application information that has been entered by the applicant, which includes at least the applicant's identity and travel destination; Based on the applicant's identity and the travel destination, retrieve historical travel application records that are the same as or similar to the travel destination from the historical travel database; Extract itinerary data fields from retrieved historical travel application records; The extracted itinerary data fields are used as recommended options to generate a populate suggestion list and push it to the application end; In response to receiving a confirmation instruction from the application client for any of the recommended options in the suggestion list, the corresponding itinerary data field value is automatically filled into the corresponding field position of the travel application data; After the data is filled in, receive the complete travel request data.

[0052] It should be noted that, in the embodiments of the present invention, if the above-described processing method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, 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 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 methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of the present invention are not limited to any specific hardware and software combination.

[0053] Accordingly, embodiments of the present invention provide a storage medium storing a computer program thereon, characterized in that the computer program, when executed by a processor, implements the steps in the processing method provided in the above embodiments.

[0054] This invention provides an electronic device; Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, the electronic device 100 includes: a processor 101, at least one communication bus 102, a user interface 103, at least one external communication interface 104, and a memory 105. The communication bus 102 is configured to enable communication between these components. The user interface 103 may include a display screen, and the external communication interface 104 may include standard wired and wireless interfaces. The processor 101 is configured to execute a program of a processing method stored in the memory to implement the steps of the processing method provided in the above embodiments.

[0055] It should be noted that the descriptions of the storage medium and electronic device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of the present invention, please refer to the descriptions of the method embodiments of the present invention for understanding.

[0056] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of the invention, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the invention. The sequence numbers of the above-described embodiments of the invention are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0057] 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, object, 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, object, 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, object, or apparatus that includes that element.

[0058] In the several embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0059] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0060] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0061] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0062] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, 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 controller to execute all or part 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 mobile storage devices, ROMs, magnetic disks, or optical disks.

[0063] The above description is merely an 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 method for adaptive processing of travel approvals, the method comprising: receiving a travel request; determining a travel approval process for the travel request; and processing the travel request according to the travel approval process. include: Receive travel application data initiated by applicants; Obtain the applicant's historical travel history as a dataset, and calculate the applicant's credit score based on the historical travel history dataset; Extract the itinerary features from the travel application data, and calculate the itinerary risk score based on the itinerary features; Based on the credit score and the trip risk score, a target travel approval path is dynamically selected from multiple predefined approval path templates; The approval process for the travel application data is executed according to the target travel approval path.

2. The method of claim 1, wherein, The step of obtaining the applicant's historical travel data as a dataset and calculating the applicant's credit score based on the historical travel data dataset includes: Obtain the applicant's historical travel history as a dataset, wherein the historical travel history dataset includes the applicant's most recent travel history before the current time. The single behavioral scoring sequence corresponding to each business travel application ; According to the time decay weight formula Assign weights to each historical travel application, among which , For the current time, For the first The time when the travel application was submitted. The preset decay coefficient is used to control the rate at which the influence of historical behavior decays over time. The Bayesian smoothing formula is used to calculate the posterior credit status parameter : ； In the formula, is a prior weight, used to control the strength of the group prior information; is a group credit prior mean; mapping the posterior credit status parameter by a normalization function to the 0-100 interval, resulting in the credit score : ； wherein and are the benchmark mean and benchmark standard deviation of the population credit status distribution, respectively.

3. The method of claim 2, wherein, the single behavior score is calculated by the following equation: ； In the formula, For a binary variable, when the first... The value is 1 if the travel application is approved on the first attempt, and 0 otherwise. This represents a negative mapping of the degree of cost exceeding the limit, where For the first The actual cost of this business trip. The corresponding standard fee; This indicates the penalty for the number of itinerary changes, among which... For the first Number of itinerary changes for this business trip; , indicating penalties for approval delays, among which For the first The approval process for this business trip took a long time. This represents the average approval time of the system. , , , , These are preset positive weighting coefficients, used to control the degree of influence of each behavioral indicator on a single behavioral score.

4. The method of claim 1, wherein, The step of extracting travel application data for itinerary features and calculating a travel risk score based on the itinerary features includes: extracting a plurality of trip feature raw values from the travel request data ; For each trip feature, a logistic membership function is used to calculate the corresponding risk factor : ； wherein, is a preset slope parameter, is a preset risk highlighting threshold, ; The risk factors are fused by an accumulative risk probability model to obtain a joint risk probability : ； The system detects whether the travel features contain a preset high-risk combination; if so, it calculates a cross-enhancement term. ,in For the first The enhancement coefficient of the combination, For indicator functions, when the first The value is 1 when a high-risk combination occurs, and 0 otherwise. computing the trip risk score : 。 5. The method of claim 1, wherein, The step of dynamically selecting a target travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score includes: Based on the type identifier of the travel application data, a target two-dimensional decision matrix is ​​determined from a plurality of preset two-dimensional decision matrices; wherein, the plurality of preset two-dimensional decision matrices correspond to different types of travel applications, and each two-dimensional decision matrix has an independent credit score interval division, itinerary risk score interval division, and mapping relationship between decision area and approval path template; The credit score and travel risk score are mapped to the target two-dimensional decision matrix to determine the target decision region in the target two-dimensional decision matrix; Based on the target decision area, select the corresponding target approval path template from multiple predefined approval path templates to determine the target travel approval path.

6. The method of claim 1, wherein, Also includes: After receiving the travel application data, the integrity of the travel application data is checked; the integrity check includes: detecting whether the travel application data is missing any preset required fields; In response to the detection of any missing required field, a missing field prompt message is generated and returned to the application end until the complete travel application data is received.

7. The method of claim 1, wherein, Also includes: Obtain the preset approval time limit of the current approval node in the target travel approval path; Start a timer to monitor the actual time consumed by the current approval node; When the actual time consumed exceeds the preset approval time limit and no approval result is received, an overdue reminder message is automatically sent to the approver at the current approval node; If no approval result is received within the preset waiting time after the timeout reminder message is sent, the travel application data will be automatically transferred to the backup approver of the current approval node, and the current approval node in the target travel approval path will be updated to the backup approver node.

8. The method of claim 1, wherein, Also includes: After generating the target travel approval path, the budget pool identifier associated with each approval node is queried based on the set of approval nodes of the target travel approval path. Based on the estimated cost information of the travel application data, the corresponding budget amount is pre-deducted from the budget pool corresponding to the budget pool identifier to generate a budget pre-occupancy record; If the approval result is rejected at any point in the approval process, the budget pre-allocation record will be released and the pre-deducted budget amount will be returned to the corresponding budget pool. If the entire approval process is completed, the budget pre-allocation record will be converted into an actual budget deduction record.

9. The method of claim 1, wherein, Also includes: Before receiving the travel application data, obtain partial application information that has been entered by the applicant, which includes at least the applicant's identity and travel destination; Based on the applicant's identity and the travel destination, retrieve historical travel application records that are the same as or similar to the travel destination from the historical travel database; Extract itinerary data fields from retrieved historical travel application records; The extracted itinerary data fields are used as recommended options to generate a populate suggestion list and push it to the application end; In response to receiving a confirmation instruction from the application client for any of the recommended options in the suggestion list, the corresponding itinerary data field value is automatically filled into the corresponding field position of the travel application data; After the data is filled in, receive the complete travel request data.

10. A travel approval adaptive processing system, characterized by, include: The receiving module is used to receive travel application data initiated by the applicant; The credit scoring module is used to obtain the applicant's historical travel data set and calculate the applicant's credit score based on the historical travel data set. The risk scoring module is used to extract the itinerary features from the travel application data and calculate the itinerary risk score based on the itinerary features; The selection module is used to dynamically select a target travel approval path from multiple predefined approval path templates based on the credit score and the travel risk score. The execution module is used to execute the approval process of the travel application data according to the target travel approval path.

Images