A method, device, electronic device and storage medium for allocating business personnel

Abstract

The present invention discloses a business personnel allocation method, device, electronic device and storage medium, and relates to the field of data processing technology. The method comprises: obtaining a matching business prediction model according to a business goal; sending a customer set and a business personnel set to the business prediction model to obtain a prediction allocation result through the business prediction model; parsing the prediction allocation result through a decision planning method according to the business goal and the business constraint set, so as to allocate a corresponding business personnel to each customer. The technical solution of the embodiment of the present invention not only improves the allocation efficiency of business personnel, reduces the manpower cost and time cost of business personnel allocation, but also improves the matching degree between business personnel and customers, and ensures smooth communication between business personnel and customers.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a business personnel allocation method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous development of society, the business types of various institutions have begun to become diversified, which requires the allocation of corresponding business personnel to different customer groups in order to achieve targeted business processing.

[0003] In the prior art, when business personnel are assigned to different customers, it is usually based on manual experience and uniformly assigned by management personnel, or automatically assigned based on some simple management rules. For example, according to the number of customers currently undertaken by the business personnel, they are sorted from few to many, and business personnel with fewer customers are given priority to take on new customers to ensure that the number of customers for each business personnel is balanced.

[0004] However, this way of allocating business personnel not only has low allocation efficiency and requires high manpower and time costs, but also has poor allocation results. It ignores the degree of matching between business personnel and customers, often leading to poor communication between business personnel and customers, which in turn leads to problems such as slow business progress and low business processing efficiency. Summary of the invention

[0005] The present invention provides a business personnel allocation method, device, electronic equipment and storage medium to solve the problem of mismatch between customers and allocated business personnel.

[0006] According to one aspect of the present invention, a method for allocating business personnel is provided, comprising:

[0007] Acquire at least one matching business prediction model according to the business objective;

[0008] Sending the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer in the prediction allocation result is matched with at least one business personnel;

[0009] According to the business objectives and business constraint sets, the forecast allocation results are analyzed by a decision planning method to allocate a corresponding business person to each customer.

[0010] The business prediction model includes a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model.

[0011] The business objectives include a first business objective oriented towards customer scale, a second business objective oriented towards short-term business quantity, and a third business objective oriented towards long-term business quantity; the first business objective matches the business conversion rate prediction model; the second business objective matches the business conversion rate prediction model and the business conversion quantity prediction model; the third business objective matches the business conversion rate prediction model, the business conversion quantity prediction model and the business continuation rate prediction model.

[0012] The predicted allocation result is parsed by a decision planning method according to the business objective and the business constraint set, including: obtaining a matching target business constraint set according to the business objective, and parsing the predicted allocation result by a decision planning method according to the business objective and the target business constraint set.

[0013] The sending of the customer set and the business personnel set to the at least one business prediction model to obtain the prediction allocation result through the at least one business prediction model includes: obtaining multiple customer subsets in the customer set, and obtaining multiple business personnel subsets in the business personnel set; sending each of the customer subsets and each of the business personnel subsets to the at least one business prediction model to obtain the prediction allocation result through the at least one business prediction model; wherein each customer subset in the prediction allocation result is matched with a business personnel subset.

[0014] After assigning a corresponding business person to each customer, the method further includes: for the current customer, recommending matching business types and question-and-answer information to the assigned business person.

[0015] According to another aspect of the present invention, there is provided a business personnel allocation device, comprising:

[0016] A prediction model acquisition module, used to acquire at least one matching business prediction model according to a business objective;

[0017] An allocation result acquisition module, used for sending a customer set and a business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer in the prediction allocation result is matched with at least one business personnel;

[0018] The constraint parsing execution module is used to parse the predicted allocation result through a decision planning method according to the business objectives and the business constraint set, so as to allocate a corresponding business person to each customer.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the business personnel allocation method described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the business personnel allocation method described in any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the business personnel allocation method according to any embodiment of the present invention is implemented.

[0025] The technical solution of the embodiment of the present invention, after obtaining a matching business prediction model according to the business goal, sends the customer set and the business personnel set to the business prediction model to obtain the prediction allocation result through the business prediction model, and finally analyzes the prediction allocation result through the decision planning method according to the business goal and the business constraint set, so as to allocate a corresponding business personnel to each customer. This not only improves the allocation efficiency of business personnel, reduces the manpower cost and time cost of business personnel allocation, but also improves the matching degree between business personnel and customers, ensures smooth communication between business personnel and customers, and avoids the problems of slow business progress and low business handling efficiency caused by the mismatch between business personnel and customers.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] 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.

[0028] Figure 1 is a flow chart of a business personnel allocation method provided according to Embodiment 1 of the present invention;

[0029] Figure 2 is a flow chart of another method for allocating business personnel provided according to Embodiment 2 of the present invention;

[0030] Figure 3 is a flow chart of another method for allocating business personnel provided according to Embodiment 3 of the present invention;

[0031] Figure 4 is a structural schematic diagram of a business personnel allocation device provided according to a fourth embodiment of the present invention;

[0032] Figure 5 It is a structural schematic diagram of an electronic device for implementing the business personnel allocation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention 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 device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 This is a flowchart of a business personnel allocation method provided in the first embodiment of the present invention. This embodiment can be applied to allocate business personnel to customers based on the business prediction model and decision planning method. The method can be executed by the business personnel allocation device in any embodiment of the present invention. The business personnel allocation device can be implemented in the form of hardware and / or software. The business personnel allocation device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0037] S101. Acquire at least one matching business prediction model according to a business objective.

[0038] Business goals are formulated based on actual business needs, which represent the business objectives that are expected to be achieved after business personnel are assigned to customers. For example, business processing efficiency is used as a business goal, that is, less time is spent on processing one or a specified number of businesses. Therefore, after corresponding business personnel are assigned to customers, the business processing efficiency can be accelerated. Business goals are guided by the number of positive customer reviews. Therefore, after corresponding business personnel are assigned to customers, higher customer satisfaction can be ensured.

[0039] Different business objectives correspond to one or more business prediction models. Each business prediction model is trained based on different sample sets. There are both identical samples and different samples between different sample sets. If a sample meets the training requirements of multiple business prediction models at the same time, the sample can be included in the sample sets corresponding to the above-mentioned multiple business prediction models at the same time. Each sample is a mapping relationship between a customer and a business person, that is, one customer is matched with one business person. Among them, each customer can only be assigned one business person, and one business person can undertake multiple customers.

[0040] Each sample set consists of positive samples and negative samples; after the current business personnel is assigned to the customer in the positive sample, the final business processing process can achieve the business goal or the degree of completion of the business goal is high; after the current business personnel is assigned to the customer in the negative sample, the final business processing process cannot achieve the business goal or the degree of completion of the business goal is low; taking the above technical solution as an example, the business goal is business processing efficiency, the combination relationship of customers and business personnel in the positive sample, the business processing efficiency after the combination is high (that is, greater than or equal to the preset efficiency threshold); while the combination relationship of customers and business personnel in the negative sample, the business processing efficiency after the combination is low (that is, less than the preset efficiency threshold).

[0041] The customer information of each customer in the sample includes customer relationship information and customer portrait; among which, customer relationship information includes information about people who have an acquaintance relationship with the customer, such as relative information, friend information and colleague information; customer portrait includes personal information such as occupation, age, education, interests and hobbies, permanent residence and marital status; the business personnel information of each business personnel in the sample includes customer set information and business personnel portrait; among which, customer set information includes customer information that the business personnel has currently undertaken, or customer information that has been undertaken in the past; business personnel portrait includes personal information such as age, length of service, length of company life, business conversion rate, number of business conversions and business continuation rate.

[0042] Different business prediction models can determine the model category of the business prediction model (for example, a binary classification model and a regression model) according to their different prediction needs, and then select the corresponding algorithm according to the model category to pre-build it; after the sample set is input into the constructed business prediction model, the business prediction model automatically mines effective feature combinations to establish the feature relationship between customer information (i.e., customer relationship information and customer portrait) and matching business personnel information (customer set information and business personnel portrait), thereby completing the pre-training of the business prediction model.

[0043] S102. Send the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer in the prediction allocation result is matched with at least one business personnel.

[0044] The customer collection is a collection of customers in the business system waiting for business personnel to be assigned, including newly added customers in the business system and original customers whose original business relationships have ended and for whom no new business personnel have been assigned. Once a corresponding business personnel is assigned to a customer, the customer will be removed from the customer collection. Each customer in the customer collection includes corresponding customer information, namely, the customer relationship information and customer portrait in the above technical solution.

[0045] The business personnel set is a set of business personnel in the business system who can continue to undertake customer reception tasks, that is, a set of business personnel whose customer reception number is not saturated. Once the number of customers accepted by a business personnel reaches saturation, the business personnel will be removed from the business personnel set. When the number of customers accepted by the business personnel reaches an unsaturated state again, the business personnel will be added to the business personnel set again. Each business personnel in the business personnel set includes corresponding business personnel information, that is, the customer set information and business personnel portrait in the above technical solution.

[0046] After sending the customer set and the business personnel set to the business prediction model, the pre-trained business prediction model has the function of assigning business personnel to customers based on the characteristic relationship between customer information and matching business personnel information; if the business prediction model is a binary classification model, the classification probability represents the degree of match between the customer and the business personnel, that is, the greater the classification probability, the higher the degree of match; if the business prediction model is a regression model, the value of its calculation result represents the degree of match between the customer and the business personnel, that is, the greater the value of the above calculation result, the higher the degree of match.

[0047] When allocating business personnel to customers through the business prediction model, you can specify the allocation quantity (i.e., the first quantity threshold), that is, allocate business personnel of the first quantity threshold to the current customer as candidate business personnel; you can also specify a classification probability threshold or a calculated value threshold, that is, all business personnel greater than or equal to the classification probability threshold or the calculated value threshold are regarded as candidate business personnel; the matching relationship between a customer and one or more candidate business personnel is the predicted allocation result of the business prediction model.

[0048] S103: According to the business objectives and business constraint sets, the predicted allocation results are analyzed by a decision planning method to allocate a corresponding business person to each customer.

[0049] The business constraint set includes multiple business constraint rules, and the business constraint rules are pre-defined matchable rules or unmatchable rules; for example, the blacklist constraint rule stipulates that specific customers or specific types of customers cannot be undertaken by specific business personnel or specific types of business personnel to avoid the occurrence of phenomena such as excessive age differences and excessively high complaint rates; the work compliance constraint rule stipulates the limit on the number of customers that each business personnel can undertake; the regional constraint rule stipulates that the distance between the customer and the business personnel's permanent residence cannot be too large; the docking relationship constraint rule stipulates that a customer can only be undertaken by one business personnel. Optionally, in the embodiment of the present invention, the specific content of the business constraint rule is not limited.

[0050] The business goal is defined as the optimization goal of the decision problem, and the business constraint set is used as the constraint condition. The matching relationship between a customer and multiple business personnel is matched, and finally the matching relationship between a customer and a business personnel is obtained. In fact, the above problem has been transformed into a decision planning problem (i.e., a nonlinear integer programming problem). Therefore, it can be solved by using heuristic algorithms (e.g., simulated annealing, genetic algorithms, example algorithms) or non-heuristic solvers (e.g., COPT (COptimizer) solver, APOPT solver, IPOPT (Interior Point OPTimizer) solver, etc.). The optimal solution obtained by solving the problem is to assign a corresponding business personnel to each customer.

[0051] Optionally, in an embodiment of the present invention, the prediction allocation result is parsed by a decision planning method according to the business objectives and the business constraint set, including: parsing the prediction allocation result by a decision planning method according to the business objectives and the business constraint set. Specifically, when the business objectives change, the corresponding business constraints may also change, so different business constraints can be pre-established for different business objectives, so as to improve the accuracy of the parsing results when the prediction allocation results are parsed by the decision planning method, so as to ensure that the parsing results meet the actual business needs under the current business objectives.

[0052] Optionally, in an embodiment of the present invention, after assigning a corresponding business person to each customer, the method further includes: recommending matching business types and question-and-answer information to the assigned business person for the current customer. Specifically, after assigning a corresponding business person to each customer, the business type suitable for the customer can be obtained based on the customer information of the current customer to guide the business person to provide matching business services to the customer, improve the work efficiency of the business person, and improve the business conversion rate; at the same time, matching question-and-answer information can also be obtained based on the current business type and customer information to guide the business person to provide professional business services to the customer based on the above question-and-answer information to improve the service quality.

[0053] The technical solution of the embodiment of the present invention, after obtaining a matching business prediction model according to the business goal, sends the customer set and the business personnel set to the business prediction model to obtain the prediction allocation result through the business prediction model, and finally analyzes the prediction allocation result through the decision planning method according to the business goal and the business constraint set, so as to allocate a corresponding business personnel to each customer. This not only improves the allocation efficiency of business personnel, reduces the manpower cost and time cost of business personnel allocation, but also improves the matching degree between business personnel and customers, ensures smooth communication between business personnel and customers, and avoids the problems of slow business progress and low business handling efficiency caused by the mismatch between business personnel and customers.

[0054] Embodiment 2

[0055] Figure 2 This is a flow chart of a business personnel allocation method provided in Embodiment 2 of the present invention. The relationship between this embodiment and the above embodiments is that the business prediction model may include a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model. Figure 2 As shown, the method includes:

[0056] S201. Acquire at least one matching business prediction model according to the business objectives; wherein the business prediction model includes a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model; the business objectives include a first business objective oriented towards customer scale, a second business objective oriented towards short-term business quantity and a third business objective oriented towards long-term business quantity; the first business objective matches the business conversion rate prediction model; the second business objective matches the business conversion rate prediction model and the business conversion quantity prediction model; the third business objective matches the business conversion rate prediction model, the business conversion quantity prediction model and the business continuation rate prediction model.

[0057] The business conversion rate prediction model is a binary classification model. Its prediction label is whether there is at least one successful business transaction in the future (i.e., the first business time, for example, 1 week) after a new business personnel is assigned to a customer in the past; there is at least one successful business transaction between the customer in the positive sample and the business personnel they match within the first business time; and there is no successful business transaction between the customer in the negative sample and the business personnel they match within the first business time.

[0058] The business conversion rate prediction model can be constructed by using the logistic regression (LR) algorithm, the gradient boosting decision tree (GBDT) algorithm, the support vector machine (SVM) algorithm and the neural network algorithm (Neural Network Algorithm), and trained based on the sample set; the trained business conversion rate prediction model can classify the customers in the customer set and the business personnel in the business personnel set to determine whether the business personnel matches the current customer and the classification probability of each business personnel; wherein the above classification probability actually represents the matching degree between the business personnel and the current customer.

[0059] The business conversion quantity prediction model is a regression model, whose prediction label is the numerical range of the number of successful businesses handled in the future (i.e., the second business time, for example, 1 month) after new business personnel are assigned to customers in history; between customers in the positive sample and their matching business personnel, the number of successfully handled businesses in the second business time is relatively large, that is, the value of the numerical range of the number of successfully handled businesses is relatively large; between customers in the negative sample and their matching business personnel, the number of successfully handled businesses in the second business time is relatively small, that is, the value of the numerical range of the number of successfully handled businesses is relatively small.

[0060] The business conversion quantity prediction model can be constructed by using the Ridge Regression algorithm, the Gradient Boosting Regression Tree algorithm (GBRT) algorithm, the Support Vector Regression (SVR) algorithm and the neural network algorithm, and trained based on the sample set; the trained business conversion quantity prediction model can classify the customers in the customer set and the business personnel in the business personnel set, and determine the numerical range of the number of successful businesses handled between the business personnel and the current customer.

[0061] The business continuation rate prediction model is a binary classification model, whose prediction label is whether there is at least one successful business transaction in the future (i.e., the third business time, for example, 1 month) after a new business personnel is assigned to a customer in the past, and the customer will continue the business after the end of the business; between the customer in the positive sample and the matching business personnel, there is at least one successful business transaction within the third business time, and the customer will continue the business after the end of the business; between the customer in the negative sample and the matching business personnel, there is no successful business transaction within the third business time, or at least one successful business transaction, but the customer will not continue the business after the end of the business.

[0062] The business continuation rate prediction model can also be constructed using logistic regression algorithm, gradient boosting decision tree algorithm, support vector machine algorithm and neural network algorithm, and trained based on a sample set; the trained business continuation rate prediction model can classify the business personnel in the business personnel set for the customers in the customer set, determine whether the business personnel matches the current customer, and the classification probability of each business personnel; wherein the above classification probability actually represents the degree of match between the business personnel and the current customer.

[0063] The business conversion rate prediction model, business conversion quantity prediction model and business continuation rate prediction model predict the matching results between customers and business personnel based on different label information, respectively, ensuring that matching business personnel are assigned to customers under different business goals to meet business needs under different business goals, further improving the matching degree between customers and business personnel.

[0064] When the business goal is guided by customer scale, the forecast allocation results can be directly obtained based on the business conversion rate prediction model to improve the allocation efficiency of business personnel; when the business goal is guided by short-term business quantity, it is necessary to jointly predict the business personnel allocation results based on the business conversion rate prediction model and the business conversion quantity prediction model to predict both the conversion rate and the conversion quantity, thereby improving the accuracy of the business personnel allocation results; and when the business goal is guided by long-term business quantity, in addition to the business conversion rate prediction model and the business conversion quantity prediction model, it is also necessary to obtain the prediction results of the business continuation rate prediction model to further improve the matching degree between the business personnel allocation results and the current business goals.

[0065] S202. Send the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer in the prediction allocation result is matched with at least one business personnel.

[0066] S203: According to the business objectives and business constraint sets, the predicted allocation results are analyzed by a decision planning method to allocate a corresponding business person to each customer.

[0067] The technical solution of the embodiment of the present invention, the business prediction model is composed of a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model, which ensures that matching business personnel are assigned to customers under different business goals to meet business needs under different business goals, and further improves the matching degree between customers and business personnel.

[0068] Embodiment 3

[0069] Figure 3 This is a flowchart of a method for allocating business personnel provided by Embodiment 3 of the present invention. The relationship between this embodiment and the above embodiments is that the customer set is divided into multiple customer subsets, and the business personnel set is divided into multiple business personnel subsets. Figure 3 As shown, the method includes:

[0070] S301. Acquire at least one matching business prediction model according to a business objective.

[0071] S302: Acquire multiple customer subsets from the customer set, and acquire multiple business personnel subsets from the business personnel set.

[0072] For the construction of customer subsets, the management personnel can pre-determine the target parameters in the customer information based on experience values, and then divide the customers in the customer set into different customer subsets based on the target parameters; for the construction of business personnel subsets, the management personnel can also pre-determine the target parameters in the business personnel information based on experience values, and then divide the business personnel in the business personnel set into different business personnel subsets based on the target parameters.

[0073] In addition, customer subsets and business personnel subsets can also be obtained through machine learning algorithms such as metric learning; at the same time, the samples used to train the business prediction model also record the mapping relationship between customer subsets and business personnel subsets, that is, one customer subset is matched with one business personnel subset; wherein, the customer subset includes one or more customers, and the business personnel subset includes one or more business personnel.

[0074] S303. Send each of the customer subsets and each of the business personnel subsets to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer subset in the prediction allocation result is matched with a business personnel subset.

[0075] The trained business prediction model has the function of allocating a subset of business personnel to the current customer subset based on the characteristic relationship between customer information and matching business personnel information.

[0076] S304: According to the business objectives and business constraint sets, the predicted allocation results are analyzed by a decision planning method to allocate a corresponding business person to each customer.

[0077] Each customer in the customer subset is taken as a customer of the current business personnel to be assigned. According to the business objectives and business constraint sets, the mapping relationship between the above customer subset and the business personnel subset is analyzed through the decision planning method to assign a corresponding business personnel to each customer.

[0078] The technical solution of the embodiment of the present invention, after obtaining the matching business prediction model according to the business goal, obtains multiple customer subsets in the customer set and multiple business personnel subsets in the business personnel set; then sends each customer subset and each business personnel subset to the business prediction model to obtain the prediction allocation result through the business prediction model; finally, according to the business goal and the business constraint set, the prediction allocation result is parsed through the decision planning method to allocate a corresponding business personnel to each customer. In this way, the matching relationship between the customer subset and the business personnel subset is obtained, and then based on the matching relationship between the customer subset and the business personnel subset, a corresponding business personnel is allocated to each customer, thereby improving the allocation efficiency of the business personnel.

[0079] Embodiment 4

[0080] Figure 4 : is a structural block diagram of a business personnel allocation device provided by Embodiment 4 of the present invention, and the device specifically includes:

[0081] The prediction model acquisition module 401 is used to acquire at least one matching business prediction model according to the business objectives; wherein the business prediction model includes a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model; the business objectives include a first business objective oriented to customer scale, a second business objective oriented to short-term business quantity and a third business objective oriented to long-term business quantity; the first business objective matches the business conversion rate prediction model; the second business objective matches the business conversion rate prediction model and the business conversion quantity prediction model; the third business objective matches the business conversion rate prediction model, the business conversion quantity prediction model and the business continuation rate prediction model;

[0082] The allocation result acquisition module 402 is used to send the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer in the prediction allocation result is matched with at least one business personnel;

[0083] The constraint analysis execution module 403 is used to analyze the predicted allocation result according to the business goal and the business constraint set through a decision planning method to allocate a corresponding business person to each customer.

[0084] The technical solution of the embodiment of the present invention, after obtaining a matching business prediction model according to the business goal, sends the customer set and the business personnel set to the business prediction model to obtain the prediction allocation result through the business prediction model, and finally analyzes the prediction allocation result through the decision planning method according to the business goal and the business constraint set, so as to allocate a corresponding business personnel to each customer. This not only improves the allocation efficiency of business personnel, reduces the manpower cost and time cost of business personnel allocation, but also improves the matching degree between business personnel and customers, ensures smooth communication between business personnel and customers, and avoids the problems of slow business progress and low business handling efficiency caused by the mismatch between business personnel and customers.

[0085] Optionally, different business prediction models are trained based on different sample sets, and different sample sets contain the same samples and different samples.

[0086] Optionally, the customer information of each customer in the sample includes customer relationship information and customer portrait; the business personnel information of each business personnel in the sample includes customer set information and business personnel portrait.

[0087] Optionally, the constraint parsing execution module 403 is specifically used to obtain a matching target business constraint set according to the business goal, and parse the predicted allocation result through a decision planning method according to the business goal and the target business constraint set.

[0088] Optionally, the allocation result acquisition module 402 is specifically used to obtain multiple customer subsets in the customer set, and to obtain multiple business personnel subsets in the business personnel set; each of the customer subsets and each of the business personnel subsets is sent to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer subset in the prediction allocation result is matched with a business personnel subset.

[0089] Optionally, the business personnel assignment device is also used to recommend matching business types and question-and-answer information to assigned business personnel for the current customer.

[0090] The above device can execute the business personnel allocation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the business personnel allocation method provided by any embodiment of the present invention.

[0091] In the technical solutions of the embodiments of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of personal information (including customer information and business personnel information) involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] Embodiment 5

[0093] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0094] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0095] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0096] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a business personnel allocation method.

[0097] In some embodiments, the business personnel allocation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the business personnel allocation method described above may be performed. Alternatively, in other embodiments, the processor may be configured to execute the business personnel allocation method by any other appropriate means (e.g., by means of firmware).

[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or electronic device.

[0100] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein may be implemented on a heterogeneous hardware accelerator having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which a user can provide input to the heterogeneous hardware accelerator. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data electronic device), or a computing system that includes middleware components (e.g., an application electronic device), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0103] The computing system may include a client and an electronic device. The client and the electronic device are generally remote from each other and usually interact through a communication network. The relationship between the client and the electronic device is generated by computer programs running on corresponding computers and having a client-electronic device relationship with each other. The electronic device may be a cloud electronic device, also known as a cloud computing electronic device or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for allocating business personnel, characterized in that: include: At least one matching business prediction model is obtained according to the business objectives; wherein the business prediction model includes a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model; the business objectives include a first business objective oriented to customer scale, a second business objective oriented to short-term business quantity and a third business objective oriented to long-term business quantity; the first business objective matches the business conversion rate prediction model; the second business objective matches the business conversion rate prediction model and the business conversion quantity prediction model; the third business objective matches the business conversion rate prediction model, the business conversion quantity prediction model and the business continuation rate prediction model; the business The prediction label of the business conversion rate prediction model reflects whether at least one business transaction was successfully handled within the first business time after a new business person was assigned to a customer in the past; the prediction label of the business conversion quantity prediction model reflects the numerical range of the number of businesses successfully handled within the second business time after a new business person was assigned to a customer in the past; the prediction label of the business continuation rate prediction model reflects whether at least one business transaction was successfully handled within the third business time after a new business person was assigned to a customer in the past, and whether the current customer will continue the current business after the business ends; different business prediction models are trained based on different sample sets, and there are the same samples and different samples between different sample sets; Sending the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; The sending of the customer set and the business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model includes: By using a metric learning method, multiple customer subsets are obtained from a customer set, and multiple business personnel subsets are obtained from a business personnel set; Sending each of the customer subsets and each of the business personnel subsets to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer subset in the prediction allocation result is matched with a business personnel subset; According to the business objectives and business constraint sets, the forecast allocation results are analyzed by a decision planning method to allocate a corresponding business person to each customer.

2. The method according to claim 1, characterized in that The customer information of each customer in the sample includes customer relationship information and customer portrait; the business personnel information of each business personnel in the sample includes customer set information and business personnel portrait.

3. The method according to claim 1, characterized in that The step of analyzing the forecast allocation result by a decision planning method according to the business objective and the business constraint set includes: A matching target business constraint set is obtained according to the business goal, and the forecast allocation result is analyzed through a decision planning method according to the business goal and the target business constraint set.

4. The method according to claim 1, characterized in that: After assigning a corresponding business person to each customer, it also includes: For the current customer, recommend matching business types and question and answer information to the assigned business personnel.

5. A business personnel allocation device, characterized in that: include: A prediction model acquisition module, used to acquire at least one matching business prediction model according to a business objective; wherein the business prediction model includes a business conversion rate prediction model, a business conversion quantity prediction model and a business continuation rate prediction model; the business objective includes a first business objective oriented to customer scale, a second business objective oriented to short-term business quantity and a third business objective oriented to long-term business quantity; the first business objective matches the business conversion rate prediction model; the second business objective matches the business conversion rate prediction model and the business conversion quantity prediction model; the third business objective matches the business conversion rate prediction model, the business conversion quantity prediction model and the business continuation rate prediction model Matching; the prediction label of the business conversion rate prediction model reflects whether at least one business transaction was successfully handled within the first business time after a new business person was assigned to a customer in the past; the prediction label of the business conversion quantity prediction model reflects the numerical range of the number of businesses successfully handled within the second business time after a new business person was assigned to a customer in the past; the prediction label of the business continuation rate prediction model reflects whether at least one business transaction was successfully handled within the third business time after a new business person was assigned to a customer in the past, and whether the current customer will continue the current business after the business ends; different business prediction models are trained based on different sample sets, and there are the same samples and different samples between different sample sets; An allocation result acquisition module, used for sending a customer set and a business personnel set to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; The allocation result acquisition module is specifically used to obtain multiple customer subsets in the customer set and multiple business personnel subsets in the business personnel set through a metric learning method; send each of the customer subsets and each of the business personnel subsets to the at least one business prediction model to obtain a prediction allocation result through the at least one business prediction model; wherein each customer subset in the prediction allocation result is matched with a business personnel subset; The constraint parsing execution module is used to parse the forecast allocation result through a decision planning method according to the business objectives and the business constraint set, so as to allocate a corresponding business person to each customer.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the business personnel allocation method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the business personnel allocation method according to any one of claims 1 to 4 when executed.

8. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the business personnel allocation method according to any one of claims 1 to 4 is implemented.

Images