Call center order integration processing method based on data analysis

Abstract

The present invention discloses a call center order integration processing method based on data analysis, which relates to the technical field of order integration processing. The method includes: extracting call orders within a preset time window to generate basic order information; extracting historical data from call records of an order receiving module, analyzing historical order attributes in combination with a preset feature attribute set, and constructing an order identifier; analyzing order attributes to obtain an order feature attribute set; identifying the order feature attribute set using an identification branch of the order identifier to obtain a call order cluster; configuring a processing unit of an order processing module according to processing adaptability, and sending the call order cluster to the processing unit for order processing. The present invention solves the technical problem that the existing technology is difficult to cope with complex and changing customer needs and a changing market environment, resulting in poor order processing flexibility and low processing efficiency. Through data analysis, the present invention achieves the technical effect of efficient and accurate processing of call center orders.

Description

Technical Field

[0001] The present invention relates to the technical field of order integration processing, and in particular to a call center order integration processing method based on data analysis. Background Art

[0002] With the rapid development of information technology and the ubiquity of the internet, call centers, as crucial platforms for interaction between businesses and their customers, are rapidly expanding in both scale and processing capacity. Call centers must handle a massive volume of customer inquiries, complaints, and orders, ensuring they are processed efficiently, accurately, and promptly. However, traditional call center order processing methods, which primarily rely on fixed computer programs for streamlined operations, lack flexibility and intelligence, making them unable to cope with complex and ever-changing customer needs and the ever-changing market environment. Summary of the Invention

[0003] This application provides a call center order integration processing method based on data analysis, which is used to solve the technical problem that existing technologies are difficult to cope with complex and changing customer needs and the ever-changing market environment, resulting in poor order processing flexibility.

[0004] In view of the above problems, this application provides a call center order integration processing method based on data analysis.

[0005] The present application provides a call center order integration processing method based on data analysis, the method comprising: an order receiving module of an interactive call center, extracting N call orders within a preset time window and generating N basic order information; extracting historical data from the call records of the order receiving module, and performing historical order attribute analysis in combination with a preset feature attribute set, and constructing an order identifier based on the analysis results, wherein the order identifier has K identification branches, each of which stores K historical order feature attribute sets and has K processing fitnesses; performing order attribute analysis on the N basic order information using the preset feature attribute set to obtain N order feature attribute sets; utilizing the K identification branches of the order identifier to identify the N order feature attribute sets to obtain M call order clusters, wherein the M call order clusters have M processing fitnesses; configuring M processing units of the order processing module based on the M processing fitnesses, and sending the M call order clusters to the M processing units for order processing.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The order receiving module of the interactive call center of the present application extracts N call orders within a preset time window and generates N basic order information; extracts historical data from the call records of the order receiving module and analyzes the historical order attributes in combination with a preset feature attribute set; constructs an order identifier based on the analysis results, wherein the order identifier has K recognition branches, each of which stores K historical order feature attribute sets and has K processing fitnesses; performs order attribute analysis on the N basic order information using the preset feature attribute set to obtain N order feature attribute sets; uses the K recognition branches of the order identifier to identify the N order feature attribute sets to obtain M call order clusters, wherein the M call order clusters have M processing fitnesses; configures M processing units of the order processing module based on the M processing fitnesses, and sends the M call order clusters to the M processing units for order processing. The present invention solves the technical problem that the existing technology is difficult to cope with complex and changing customer needs and the ever-changing market environment, resulting in poor order processing flexibility and low processing efficiency. Through data analysis, the technical effect of efficient and accurate processing of call center orders is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flowchart of a call center order integration processing method based on data analysis provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the process of constructing an order identifier based on the analysis results provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] This application provides a call center order integration processing method based on data analysis to solve the technical problem that existing technologies are difficult to cope with complex and changing customer needs and the ever-changing market environment, resulting in poor order processing flexibility and low processing efficiency. Through data analysis, the application achieves the technical effect of efficient and accurate processing of call center orders.

[0012] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0014] Example 1

[0015] like Figure 1 As shown, the present application provides a call center order integration processing method based on data analysis, the method comprising:

[0016] Step S100: The order receiving module of the interactive call center extracts N call orders within a preset time window and generates N basic order information;

[0017] In this embodiment of the present application, the order receiving module first determines a preset time window based on the business needs of the enterprise or the operational strategy of the call center. The preset time window can be the past hour, day, week, or other specific time period. After determining the preset time window, the call center's order receiving module records the start and end time points of the preset time window and extracts order data within the corresponding time range from the database.

[0018] To retrieve call orders from the database, the order receiving module connects to the call center's database and prepares to perform a query. Using SQL or another database query language, it filters the database for all eligible call orders based on the start and end time points of a pre-set time window. After extracting the call order data, the order receiving module cleans and organizes it. After this process, it generates N basic order information items.

[0019] Step S200: extracting historical data from the call records of the order receiving module, analyzing historical order attributes in combination with a preset feature attribute set, and constructing an order identifier based on the analysis results, wherein the order identifier has K identification branches, each of which stores K historical order feature attribute sets and has K processing fitness levels;

[0020] In the embodiment of the present application, historical data is first extracted from the call log of the order receiving module. The historical data contains all order information previously processed by the call center, including but not limited to order number, customer information, order time, processing time, processing results, etc.

[0021] After extracting historical data, we analyze historical orders using a pre-defined attribute set. This set of attributes is determined based on the call center's business characteristics and needs, and includes factors such as order type, customer type, and order time period. By analyzing historical orders, we determine order distribution, processing efficiency, and resource consumption based on different attribute values.

[0022] Based on the results of the historical order attribute analysis, the number of recognition branches, K, in the order identifier is determined. Each recognition branch focuses on identifying orders with a specific characteristic attribute. A representative set of historical order characteristic attributes is extracted from the historical order dataset for each recognition branch. This set of historical order characteristic attributes serves as a reference for the recognition branch to identify new call orders.

[0023] Processing fitness is a key metric for measuring the order processing efficiency and resource consumption of an order recognition branch. It is calculated based on the processing time and resource consumption of historical orders. For each recognition branch, the processing fitness calculation extracts the processing time and resource consumption data for the historical orders processed by the branch. The average processing time for the branch's historical orders is calculated by dividing the sum of the branch's historical processing time by the number of orders. The average resource consumption for the branch's historical orders is calculated by dividing the sum of the branch's historical resource consumption by the number of orders. The average processing time and average resource consumption are weighted together with pre-defined weights to determine the branch's processing fitness. The weights are adjusted based on actual conditions to reflect the importance of processing time and resource consumption in evaluating processing fitness. This calculation is repeated sequentially to obtain K processing fitness values.

[0024] Step S300: performing order attribute analysis on the N basic order information using the preset feature attribute set to obtain N order feature attribute sets;

[0025] In an embodiment of the present application, a preset feature attribute set is used to perform order attribute analysis on N basic order information, and the corresponding feature values in the preset feature attribute set are extracted from the basic information of each order. For certain non-numeric feature attributes, such as order type, customer category, etc., they are encoded and converted into numerical data. For certain feature attributes that need to be calculated, such as order processing time, they are calculated based on the relevant fields in the basic order information. The extracted, encoded and calculated feature values are combined to form a feature attribute set for each order.

[0026] Through the above steps, N order feature attribute sets are obtained, each set corresponds to an order and contains all feature values of the order under the preset feature attribute set.

[0027] Step S400: using the K identification branches of the order identifier to identify the N order feature attribute sets to obtain M call order clusters, wherein the M call order clusters have M processing fitnesses;

[0028] In this embodiment of the present application, N sets of order attribute characteristics are loaded into the order identifier in preparation for recognition processing. The order identifier matches the N sets of order attribute characteristics with the historical order attribute characteristics set in each recognition branch, and calculates the similarity between the order attribute characteristics set and the historical order attribute characteristics set stored in the K recognition branches one by one using cosine similarity.

[0029] When the similarity between an order feature attribute set and a certain identification branch, for example, a historical order feature attribute set stored in the first identification branch, meets a preset similarity threshold, the order feature attribute set is stored in an internal node corresponding to the identification branch.

[0030] As order attribute sets are assigned to internal nodes, similar orders will gradually cluster together, forming preliminary order clusters. Once all N order attribute sets have been assigned, each internal node will contain a set of order attribute sets with similar characteristics, forming a call order cluster.

[0031] The processing fitness of each call order cluster is determined based on the processing fitness of the identification branch corresponding to the cluster. By setting the processing fitness of each cluster to the processing fitness of the corresponding identification branch, a metric is provided for each order cluster to measure its processing complexity and required resources.

[0032] Finally, after the above steps, M call order clusters are obtained, each cluster contains a set of order feature attributes with similar characteristics and has corresponding processing fitness.

[0033] Step S500: configuring M processing units of the order processing module according to the M processing fitnesses, and sending M call order clusters to the M processing units for order processing.

[0034] In this embodiment of the present application, the order processing module includes multiple processing units, which initially have the same processing capabilities and resource allocation. Based on the processing adaptability of the call order cluster, the processing requirements, efficiency requirements, and resource consumption of each cluster are analyzed. Based on the analysis results, a corresponding processing unit is configured for each call order cluster. Configuration includes adjusting resource allocation of processing units, setting processing priorities, and optimizing processing flows.

[0035] When allocating resources, we rationally allocate resources to processing units based on resource utilization and estimated resource consumption in the processing fitness, ensuring efficient resource utilization during processing. When setting processing priorities, we assign different processing priorities to processing units based on the time weight and order urgency in the processing fitness, ensuring that urgent or important orders are processed promptly. When optimizing processing flows, we optimize the processing flow of processing units based on the characteristics and attributes of call order clusters to improve processing efficiency.

[0036] Further, such as Figure 2 As shown, step S200 in the method provided in the application embodiment further includes:

[0037] Extracting historical data from the call records of the order receiving module to obtain multiple historical call order data sets, wherein the multiple historical call order data sets include multiple historical order basic information and multiple historical processing fitness levels;

[0038] Extracting attributes from the plurality of historical call order data sets using the preset characteristic attribute set as an index to obtain a plurality of historical order characteristic attribute sets;

[0039] Based on the multiple historical order feature attribute sets and the multiple historical processing fitness levels, similar identification is performed to construct the order identifier.

[0040] In this embodiment of the present application, historical data is extracted from the call logs of the order receiving module. Historical data related to order processing is filtered from the call logs, including basic historical order information and historical processing fitness. After filtering and cleaning, the resulting historical data is organized into multiple historical call order data sets. Each set contains complete basic historical order information and the corresponding historical processing fitness.

[0041] Using the preset feature attribute set as an index, the corresponding feature attributes are extracted from the historical call order data set. After attribute extraction, multiple historical order feature attribute sets are obtained. Each set contains historical order features corresponding to the preset feature attribute set.

[0042] Based on the set of historical order feature attributes and historical processing fitness, an appropriate similarity identification algorithm is selected. For example, cluster analysis or classification algorithms can be used to identify orders with similar characteristics and processing fitness. The selected similarity identification algorithm is then applied to the set of historical order feature attributes to identify order categories with similar characteristics. Based on the similarity identification results, an order identifier is constructed. The order identifier consists of multiple identification branches, each corresponding to an identified order category. Each branch stores the set of historical order feature attributes and the corresponding historical processing fitness for that category.

[0043] Furthermore, based on the multiple historical order feature attribute sets and the multiple historical processing fitnesses, similarity identification is performed to construct the order identifier, and the method further includes:

[0044] Randomly extracting a first historical order feature attribute set from the multiple historical order feature attribute sets without replacement and storing the set in a first identification branch, wherein the first identification branch has a first internal node and a first external node, and the first identification branch is used to perform binary classification on the multiple historical order feature attribute sets;

[0045] Using the first identification branch to identify the multiple historical order feature attribute sets, determine whether the similarity between the multiple historical order feature attribute sets and the first historical order feature attribute set stored in the first identification branch meets a preset similarity threshold, and if so, add them to the first internal node; if not, add them to the first external node;

[0046] A second set of historical order feature attributes is randomly selected from the multiple sets of historical order feature attributes of the first external node without replacement and stored in a second identification branch, wherein the second identification branch has a second internal node and a second external node, and the second identification branch is used to perform binary classification on the multiple sets of historical order feature attributes of the first external node.

[0047] In an embodiment of the present application, a set of historical order attribute characteristics is randomly extracted without replacement from multiple sets of historical order attribute characteristics to serve as the initial classification basis. The extracted set of historical order attribute characteristics is stored in a first identification branch. The first identification branch is the starting branch of the order identifier and is used to perform preliminary binary classification on multiple subsequent sets of historical order attribute characteristics. Each identification branch has internal nodes and external nodes. The internal nodes store sets of historical order attribute characteristics similar to the branch, while the external nodes store sets of historical order attribute characteristics dissimilar to the branch.

[0048] Using the historical order attribute set stored in the first identification branch, the remaining multiple historical order attribute sets are identified by calculating similarity using cosine similarity. For each historical order attribute set, a determination is made as to whether its similarity with the historical order attribute set stored in the first identification branch meets a preset similarity threshold. The preset similarity threshold is set based on business requirements and order characteristics and is used to determine which orders should be classified into the same branch. If the similarity meets the threshold, the historical order attribute set is similar to the set in the first identification branch and is added to the first internal node. If the threshold is not met, it indicates that the historical order attribute set is not similar and is added to the first external node.

[0049] When the number of historical order attribute sets from the first external node reaches a certain level, such as exceeding a preset value, a new set of historical order attribute sets is randomly extracted from the first external node's multiple sets without replacement to serve as a new classification basis. This extracted set of historical order attribute sets is stored in a new recognition branch, namely, the second recognition branch, and similarly processed. The second recognition branch is used to further perform binary classification on the multiple historical order attribute sets from the first external node.

[0050] This process is repeated recursively, each time extracting a new set of historical order attribute characteristics from the external nodes as a new classification basis, creating a new recognition branch, and further classifying the remaining sets. This continues until all historical order attribute characteristics are classified into the corresponding internal nodes, or other stopping conditions are met, such as the number of branches reaching the upper limit or the classification effect no longer improving.

[0051] Furthermore, the method further comprises:

[0052] Randomly extracting the K-1th historical order feature attribute set from the multiple historical order feature attribute sets of the K-2th external node without replacement and storing it in the K-1th identification branch, wherein the K-1th identification branch has the K-1th internal node and the K-1th external node, and the K-1th identification branch is used to perform binary classification on the multiple historical order feature attribute sets of the K-2th external node;

[0053] Storing the multiple historical order feature attribute sets in the K-1th external node into the Kth internal node of the Kth identification branch;

[0054] The order identifier is constructed according to the first identification branch, the second identification branch, the K-1th identification branch, the Kth identification branch, the first internal node, the second internal node, the K-1th internal node and the Kth internal node.

[0055] In this embodiment, when the K-1th round is reached, one of the multiple historical order feature attribute sets of the external nodes of the K-2th round is randomly selected without replacement as the K-1th historical order feature attribute set. This set is used as the new classification basis for further binary classification of the sets in the external nodes of the K-2th round.

[0056] Create a new identification branch, the K-1th identification branch. This branch has two nodes: the K-1th internal node and the K-1th external node. The K-1th internal node is used to store historical order attribute sets that are similar to the K-1th historical order attribute set, while the K-1th external node is used to store dissimilar sets.

[0057] Using the K-1th identification branch, the similarity between each set and the K-1th set of historical order attribute characteristics is calculated, and they are classified into the K-1th internal node or the K-1th external node based on the preset similarity threshold. Multiple historical order attribute sets in the K-2th external node are binary classified.

[0058] After a certain round of classification, if a stopping condition is reached, such as the number of historical order feature attribute sets in the K-1th external node is less than a preset value, or the classification effect no longer improves significantly, no new recognition branches will be created. Instead, the set in the current external node will be stored in the internal node of the next recognition branch.

[0059] When the stopping condition is met, the multiple historical order attribute sets in the K-1th external node are stored in the Kth internal node of the Kth identification branch. The Kth identification branch is the last identification branch and is used to store historical order attribute sets that cannot be further subdivided.

[0060] Finally, the first recognition branch, the second recognition branch, ..., the K-1th recognition branch and the Kth recognition branch are combined to form an order recognizer structure.

[0061] Furthermore, the method further comprises:

[0062] Obtaining a plurality of first processing fitnesses corresponding to a plurality of historical order feature attribute sets within the first internal node;

[0063] Calculating a first mean value of the plurality of first processing fitnesses to generate a first concentration point;

[0064] Calculating a first variance of the plurality of first processing fitnesses, comparing the first variance with a preset variance, and multiplying the ratio by a preset concentration step length to obtain a first concentration step length;

[0065] Counting the number of historical order feature attribute sets within an area centered on the first concentration point and with the first concentration step length as a radius to obtain a first concentration value;

[0066] The second concentrated point is obtained by moving in any direction with the first concentrated point as a starting point according to the first concentrated step size.

[0067] In this embodiment of the present application, each internal node of the order identifier stores a set of historical order attribute properties corresponding to that node, and these sets are associated with respective processing fitnesses. These historical order attribute sets are retrieved from the first internal node, and their respective corresponding first processing fitnesses are obtained.

[0068] Calculate the mean of the first processing fitness corresponding to the set of characteristic attributes of all historical orders in the first internal node to obtain a value representing the average processing effect of orders in the node, that is, the first concentration point.

[0069] After calculating the first mean, the deviation of each process fitness from the mean is calculated. The squared values of these deviations are summed, and the sum is divided by the number of process fitnesses to obtain the first variance. The calculated first variance is compared with the preset variance to obtain a ratio. This ratio reflects the relative relationship between the actual dispersion of the process fitness and the expected dispersion. The preset variance is a pre-set threshold that reflects the expected fluctuation range of the process fitness in a business scenario or order processing system. Finally, the ratio is multiplied by the preset concentration step size to obtain the first concentration step size. The preset concentration step size is the parameter for the moving or exploration step size during the quantitative analysis process.

[0070] A circular area is defined with the first concentration point as the center and the first concentration step size as the radius. Next, the number of historical order attribute sets within this area is counted. This number is called the first concentration quantity.

[0071] The first concentrated point is taken as the starting point, and the first concentrated step is used as the moving step to move in any direction. The new point after the movement is called the second concentrated point.

[0072] Furthermore, the method further comprises:

[0073] determining whether the first concentration amount of the first concentration point is greater than the second concentration amount of the second concentration point, and if so, updating the second concentration point as the starting point;

[0074] If not, a first flight factor is obtained based on a flight factor generator. When the first flight factor is greater than a preset value, the first concentrated point is used as a starting point and the third concentrated point is obtained by moving in any direction except the second concentrated point according to the first concentrated step size.

[0075] When the first flight factor is less than or equal to a preset value, updating the second concentration point as the starting point;

[0076] After the number of movements meets the preset number, the first processing fitness corresponding to the maximum value of the concentration during the movement is used as the processing fitness of the first internal node.

[0077] In this embodiment of the present application, a circular area is first determined with the second concentration point as the center and the first concentration step size as the radius. Next, the number of historical order feature attribute sets within this area is counted, and the counted number is referred to as the second concentration volume. The order processing fitness concentration volume around the first concentration point and the second concentration point is compared. If the first concentration volume of the first concentration point is greater than the second concentration volume of the second concentration point, it indicates that there are more orders with similar processing fitness around the first concentration point. Therefore, the second concentration point is updated as the starting point.

[0078] If the first concentration value of the first concentration point is not greater than the second concentration value of the second concentration point, a first flight factor is obtained based on a flight factor generator. The flight factor generator is a function specifically used to generate flight factors. It generates an appropriate flight factor based on a preset rule or algorithm, combined with information such as the current search history and the processed fitness distribution.

[0079] When the first flight factor is greater than the preset value, the current search state is inclined to explore new areas. Therefore, starting from the first focus point, the search moves in any direction other than the second focus point according to the first focus step size to obtain the third focus point. This avoids repeated searches near the already explored second focus point and expands the search range to explore other possible focus areas.

[0080] When the first flight factor is less than or equal to the preset value, it indicates that the current search state is more inclined to utilize the existing information. Therefore, the second focus point is updated as the starting point.

[0081] To avoid infinite loops or excessive searching, a preset number of moves is set. When this number is reached, the search process stops and the processing fitness of the first internal node is determined based on the information recorded during the moves. Specifically, the concentration values obtained during all moves are compared to find the first processing fitness corresponding to the maximum concentration value. This processing fitness best represents the overall processing performance of orders within that internal node and is therefore used as the processing fitness of the first internal node.

[0082] Furthermore, the method further comprises:

[0083] The flight factor generator includes a flight factor generation formula, wherein the flight factor generation formula is:

[0084] ;

[0085] in, For the flight factor, Randomly generated values for the rand function. .

[0086] In the embodiment of the present application, by introducing random numbers By combining the sine function and the adjustment of the exponential function, the formula generates a series of flight factors with different characteristics and behaviors, which helps the search algorithm find a balance between exploration and exploitation and improves search efficiency and effect.

[0087] Furthermore, step S500 in the method provided in the application embodiment further includes:

[0088] Interactively obtain computing resources of the order processing module to obtain available computing resources;

[0089] Calculating the ratio of the M processing fitnesses to the sum of the M processing fitnesses respectively, and multiplying the ratio by the available computing power resources to obtain M computing power allocation results;

[0090] The M processing units of the order processing module are configured based on the M computing power allocation results.

[0091] In this embodiment of the present application, the system interacts with the order processing module to obtain information about available computing resources. This information is analyzed to understand the hardware configuration and performance of the current module. Factors such as the current order processing module's task load, the occupancy of other modules, and system maintenance requirements are considered. Taking all of these factors into consideration, the system calculates the current amount of available computing resources.

[0092] Each processing unit is evaluated for its fitness to determine its efficiency and ability to process specific order tasks. Each processing unit's fitness is compared with the sum of all processing units' fitness, resulting in M ratios. These ratios are then multiplied by the available computing resources to determine the amount of computing resources each of the M processing units should receive.

[0093] Finally, based on the M computing power allocation results obtained, each processing unit is allocated a corresponding number of processor cores, memory, and storage resources to ensure that they can work according to the expected computing power requirements.

[0094] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0095] The order receiving module of the interactive call center of the present application extracts N call orders within a preset time window and generates N basic order information; extracts historical data from the call records of the order receiving module and analyzes the historical order attributes in combination with a preset feature attribute set; constructs an order identifier based on the analysis results, wherein the order identifier has K recognition branches, each of which stores K historical order feature attribute sets and has K processing fitnesses; performs order attribute analysis on the N basic order information using the preset feature attribute set to obtain N order feature attribute sets; uses the K recognition branches of the order identifier to identify the N order feature attribute sets to obtain M call order clusters, wherein the M call order clusters have M processing fitnesses; configures M processing units of the order processing module based on the M processing fitnesses, and sends the M call order clusters to the M processing units for order processing. The present invention solves the technical problem that the existing technology is difficult to cope with complex and changing customer needs and the ever-changing market environment, resulting in poor order processing flexibility and low processing efficiency. Through data analysis, the technical effect of efficient and accurate processing of call center orders is achieved.

[0096] It should be noted that the above-mentioned order of the embodiments of the present application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0098] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A call center order integration processing method based on data analysis, characterized in that: The method comprises: The order receiving module of the interactive call center extracts N call orders within a preset time window and generates N basic order information; Extracting historical data from the call records of the order receiving module, analyzing historical order attributes in combination with a preset feature attribute set, and constructing an order identifier based on the analysis results, wherein the order identifier has K identification branches, each of which stores K historical order feature attribute sets and has K processing fitness levels; Performing order attribute analysis on the N basic order information using the preset characteristic attribute set to obtain N order characteristic attribute sets; Using the K identification branches of the order identifier to identify the N order feature attribute sets, obtaining M call order clusters, wherein the M call order clusters have M processing fitnesses; configuring M processing units of the order processing module according to the M processing fitnesses, and sending the M call order clusters to the M processing units for order processing; The method comprises: Acquire multiple first processing fitnesses corresponding to multiple historical order feature attribute sets within a first internal node of the identification branch; Calculating a first mean value of the plurality of first processing fitnesses to generate a first concentration point; Calculating a first variance of the plurality of first processing fitnesses, and multiplying a ratio of the first variance to a preset variance by a preset concentration step length to obtain a first concentration step length; Counting the number of historical order feature attribute sets within an area centered on the first concentration point and with the first concentration step length as a radius to obtain a first concentration value; Move in any direction with the first concentrated point as the starting point according to the first concentrated step size to obtain a second concentrated point; determining whether the first concentration amount of the first concentration point is greater than the second concentration amount of the second concentration point, and if so, updating the second concentration point as the starting point; If not, a first flight factor is obtained based on a flight factor generator. When the first flight factor is greater than a preset value, the first concentrated point is used as a starting point and the third concentrated point is obtained by moving in any direction except the second concentrated point according to the first concentrated step size. When the first flight factor is less than or equal to a preset value, updating the second concentration point as the starting point; After the number of moves meets the preset number, the first processing fitness corresponding to the maximum value of the concentration during the move is used as the processing fitness of the first internal node; The flight factor generator includes a flight factor generation formula, wherein the flight factor generation formula is: ； in, For the flight factor, Randomly generated values for the rand function. .

2. The method according to claim 1, wherein Extracting historical data from the call records of the order receiving module, analyzing historical order attributes in combination with a preset feature attribute set, and constructing an order identifier based on the analysis results, the method includes: Extracting historical data from the call records of the order receiving module to obtain multiple historical call order data sets, wherein the multiple historical call order data sets include multiple historical order basic information and multiple historical processing fitness levels; Extracting attributes from the plurality of historical call order data sets using the preset characteristic attribute set as an index to obtain a plurality of historical order characteristic attribute sets; Based on the multiple historical order feature attribute sets and the multiple historical processing fitness levels, similar identification is performed to construct the order identifier.

3. The method according to claim 2, wherein Based on the multiple historical order feature attribute sets and the multiple historical processing fitnesses, similar order identification is performed to construct the order identifier, and the method includes: Randomly extracting a first historical order feature attribute set from the multiple historical order feature attribute sets without replacement and storing the set in a first identification branch, wherein the first identification branch has a first internal node and a first external node, and the first identification branch is used to perform binary classification on the multiple historical order feature attribute sets; Using the first identification branch to identify the multiple historical order feature attribute sets, determine whether the similarity between the multiple historical order feature attribute sets and the first historical order feature attribute set stored in the first identification branch meets a preset similarity threshold, and if so, add them to the first internal node; if not, add them to the first external node; A second set of historical order feature attributes is randomly selected from the multiple sets of historical order feature attributes of the first external node without replacement and stored in a second identification branch, wherein the second identification branch has a second internal node and a second external node, and the second identification branch is used to perform binary classification on the multiple sets of historical order feature attributes of the first external node.

4. The method according to claim 3, wherein The method comprises: Randomly extracting the K-1th historical order feature attribute set from the multiple historical order feature attribute sets of the K-2th external node without replacement and storing it in the K-1th identification branch, wherein the K-1th identification branch has the K-1th internal node and the K-1th external node, and the K-1th identification branch is used to perform binary classification on the multiple historical order feature attribute sets of the K-2th external node; Storing the multiple historical order feature attribute sets in the K-1th external node into the Kth internal node of the Kth identification branch; The order identifier is constructed according to the first identification branch, the second identification branch, the K-1th identification branch, the Kth identification branch, the first internal node, the second internal node, the K-1th internal node and the Kth internal node.

5. The method according to claim 1, wherein The method comprises: Interactively obtain computing resources of the order processing module to obtain available computing resources; Calculating the ratio of the M processing fitnesses to the sum of the M processing fitnesses respectively, and multiplying the ratio by the available computing power resources to obtain M computing power allocation results; The M processing units of the order processing module are configured based on the M computing power allocation results.

Images