Data processing method, data processing device, electronic equipment and storage medium

Abstract

The invention provides a data processing method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring first information; the first information comprises first business demand information of a first object and attribute information of the first object; determining a plurality of service processing resources based on the first service demand information; determining the business processing priority of the first object based on the first business demand information and / or the attribute information; determining a target service processing resource from the plurality of service processing resources based on the residual resource quantity of each service processing resource and the service processing priority; and distributing the business of the first object to the target business processing resource. According to the method and the device, the target business processing resource can be accurately and effectively determined, and the business of the first object is allocated to the target business processing resource, so that accurate processing of data is realized.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data processing method, a data processing device, an electronic device, and a computer-readable storage medium. Background Art

[0002] In data processing scenarios, there is often a need to process a large number of user businesses. It is very important to effectively process the business data of a large number of users to ensure that the business data is effectively processed while having high service quality and efficiency.

[0003] In order to solve the above problems, the existing technology usually adopts the method of obtaining the currently required business data and its historical data, and using this method to divert the business data. Although this method can achieve intelligent allocation from the perspective of historical data, it cannot mine other information of the business data to be allocated, nor can it accurately capture the priority level of the current service object, making it difficult to ensure the accuracy and effectiveness of data processing.

[0004] Therefore, how to divert business according to reasonable priority based on accurate and effective mining object information is a problem that needs to be solved urgently in the existing technology.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The present disclosure provides a data processing method, a data processing device, an electronic device and a computer-readable storage medium, thereby overcoming the problem that the prior art cannot accurately and effectively process data of object services, at least to a certain extent.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a data processing method is provided, including: obtaining first information; the first information including first business demand information of a first object and attribute information of the first object; determining multiple business processing resources based on the first business demand information; determining the business processing priority of the first object based on the first business demand information and / or the attribute information; determining a target business processing resource from the multiple business processing resources based on the remaining resource amount and the business processing priority of each of the business processing resources; and allocating the business of the first object to the target business processing resource.

[0009] According to one aspect of the present disclosure, there is provided a data processing device, including: a first information acquisition module, used to acquire first information; the first information includes first business requirement information of a first object and attribute information of the first object; a processing resource determination module, used to determine a plurality of business processing resources based on the first business requirement information; a priority determination module, used to determine the business processing priority of the first object based on the first business requirement information and / or the attribute information; a target resource determination module, used to determine a target business processing resource from the plurality of business processing resources based on the remaining resource amount and the business processing priority of each of the business processing resources; and a first object allocation module, used to allocate the business of the first object to the target business processing resource.

[0010] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above-mentioned data processing methods by executing the executable instructions.

[0011] According to one aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, any one of the above-mentioned data processing methods is implemented.

[0012] The exemplary embodiments of the present disclosure have the following beneficial effects:

[0013] It can fully mine the first information related to the first object, convert the mined first information into the business processing priority of the first object, and determine the target business processing resources of the first object based on the business processing priority, so as to accurately determine the target business processing resources for processing the business of the first object and quickly allocate the business of the first object, thereby greatly improving the data processing efficiency and effectiveness; on the other hand, according to the business demand information and / or attribute information of the first object, the business processing priority for the first object can be obtained, so as to realize the accurate capture and evaluation of the personalized needs of different first objects, and provide various data processing methods for different first objects based on the business processing priority; on the other hand, based on the business processing priority, the target business processing resources that meet the current business processing priority can be quickly determined from multiple business processing resources, thereby greatly shortening the waiting time of the first object and effectively improving the data processing experience.

[0014] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0016] Figure 1 A flow chart schematically illustrates a data processing method in this exemplary embodiment;

[0017] Figure 2 A sub-flow chart schematically illustrates a data processing method in this exemplary embodiment;

[0018] Figure 3 A sub-flow chart schematically illustrates another data processing method in this exemplary embodiment;

[0019] Figure 4 A flowchart for determining a service processing priority of a first object in this exemplary embodiment is schematically shown;

[0020] Figure 5 A flowchart schematically illustrates another data processing method in this exemplary embodiment;

[0021] Figure 6 A block diagram schematically shows a structure of a data processing device in this exemplary embodiment;

[0022] Figure 7 An electronic device for implementing the above method in this exemplary embodiment is schematically shown. DETAILED DESCRIPTION

[0023] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0024] An exemplary embodiment of the present disclosure first provides a data processing method.

[0025] The following is combined with Figure 1 This exemplary embodiment is further described as follows. Figure 1 As shown, the data processing method may include the following steps S110 to S150:

[0026] Step S110, obtaining first information; the first information includes first business requirement information of the first object and attribute information of the first object.

[0027] Among them, the first object may be a customer for whom business processing services need to be provided. In this exemplary embodiment, the first object can provide corresponding business services to the customer through a customer service session established with the customer, such as a user who initiates or receives a session. The first object may also be a user related to a specific business in a customer service session. For example, if user A insures user B, then user A and / or user B can both be the first object, etc. A customer service session refers to a session task established with a customer that requires business processing. A customer service session can be implemented in a variety of ways, such as telephone, text message, or network communication. In this exemplary embodiment, the first information of the first object can be obtained. The first information may include the first business demand information of the first object and the attribute information of the first object. The first business demand information may reflect the customer's intention to initiate a customer service session, such as negotiating repayment, initiating lending, consulting business details, and querying fault problems. The attribute information of the first object may be information reflecting the attributes of the first object, which may be information of the first object itself, such as customer level information, customer basic information, customer operation behavior information and other customer information; it may also be information related to the business of the first object, such as attribute information of financial business, etc. The specific attribute information is related to the service type, and different service types may correspond to different attribute information. For example, non-financial business may correspond to attribute information of non-financial business, etc.

[0028] In this exemplary embodiment, the first information includes the first business demand information of the first object. The first business demand information can be information expressed by the first object and related to the purpose it wants to achieve, such as the first object wants to solve the loan application, or the first object wants to inquire about the business progress, or the first object wants to unbind the account, etc. The first business demand information can be expressed by the first object in a variety of forms in the customer service session, including voice input, such as the first object inputting voice data; text input, such as the first object can enter specific intention text information in a specified dialog box, or enter character information with reference to the intention, such as character identifiers "1", "2", "3", etc. can respectively refer to specific intentions, and the first object can enter character identifiers in the customer service session to express the corresponding intention, etc., and the present disclosure does not make specific limitations on this.

[0029] Step S120: determining a plurality of business processing resources based on the first business demand information.

[0030] Business processing resources refer to business processing resources that can provide services for the first object or process the business of the first object, such as business-specific manual business processing resources, business-general manual business processing resources, or artificial intelligence business processing resources (that is, non-manual business processing resources). Among them, business-specific manual business processing resources refer to manual business processing resources used to specifically process specific first business demand information, such as business processing resources that can correspond to loan processing under the intention of lending, and business processing resources that can correspond to repayment processing under the intention of repayment. Business-specific manual business processing resources may include multiple, and the specific number is related to the first business demand information. The present disclosure does not make specific restrictions on this. Business-general manual business processing resources may be manual business processing resources used to process general first business demand information. For example, the intention to query business progress, the intention to consult business information, and the intention to solve troubleshooting can correspond to business-general manual business processing resources. Business-general manual business processing resources can be set up as one to solve general intention problems, or multiple can be set up to disperse the work pressure of business demand information processing. Artificial intelligence business processing resources may be non-manual business processing resources, such as customer service provided in the form of machine learning models or question-and-answer robots.

[0031] In an exemplary implementation, there are multiple first business demand information, the multiple first business demand information include third business demand information and at least one fourth business demand information, and the generation time of the third business demand information is later than the generation time of the fourth business demand information;

[0032] The above step S120, determining a plurality of service processing resources based on the first service requirement information, may include:

[0033] A plurality of business processing resources are determined according to the third business demand information.

[0034] In this exemplary embodiment, the first object may input first information including one or more first business demand information in the same round of customer service conversation or in different rounds of customer service conversation, for example, the first object intends to activate service A, intends to inquire about the progress of service B, or intends to terminate the progress of service C, etc. The third business demand information may refer to the main business demand information in the first information, that is, the main intention to be solved in the first business demand information conveyed by the first object. The first information also includes fourth business demand information.

[0035] When the first business requirement information includes the third business requirement information and at least one fourth business requirement information, that is, when it includes multiple business requirement information, the exemplary embodiment can determine the business requirement information for determining multiple business processing resources in multiple ways. For example, when the first object expresses multiple intentions, the last intention can be used as the target requirement, that is, the third business requirement information can be used as the business requirement information for determining multiple business processing resources, and the generation time of the third business requirement information is later than the generation time of the fourth business requirement information.

[0036] In addition, in other embodiments, the business demand information that appears most frequently can also be used as the business demand information for determining multiple business processing resources; or when the first business demand information is voice information, speech rate feature information can be extracted from multiple first business demand information, and the business demand information corresponding to the feature with the slowest speech rate can be determined as the business demand information for determining multiple business processing resources, etc.

[0037] Step S130: determining a service processing priority of the first object based on the first service requirement information and / or attribute information.

[0038] In this exemplary embodiment, the first information includes the business demand information of the first object and also includes the attribute information of the first object. In order to determine the target business processing resource from multiple candidate business processing resources, this exemplary embodiment can first determine the business processing priority of the first object based on the first business demand information and / or attribute information in the first information. Among them, the business processing priority can reflect the current service importance or service processing urgency of the first object. In this exemplary embodiment, the attribute information can also include business attribute information, behavior attribute information, etc. Therefore, when specifically determining the business processing priority of the first object, different attribute information can also be evaluated separately, and the evaluation results of each information can be integrated, and the integrated result is used as the business processing priority of the first object.

[0039] In an exemplary embodiment, the first service requirement information includes voice information, such as Figure 2 As shown, the above-mentioned determining the service processing priority of the first object based on the first service requirement information may include the following steps:

[0040] Step S210, determining the complexity of processing the business of the first object based on the degree of association between the first business requirement information and the second requirement information of the first object;

[0041] Step S220, extracting speech features from the speech information, and determining emotion information of the first object based on the speech features;

[0042] Step S230: determining the business processing priority of the first object based on the complexity and emotion information.

[0043] Among them, the second demand information may refer to historical business demand information. In actual applications, the historical business demand information of the first object in the historical customer service session may affect the first business demand information of the current customer service session. For example, when the historical demand intention is not fully resolved, or when new related demand intentions are generated based on the historical demand intentions, a new customer service session will be generated.

[0044] Based on the above reasons, and considering that the higher the complexity of the historical customer service session, the more complex the complexity of the subsequent associated customer service session will be, this exemplary embodiment can determine the complexity of processing the business of the first object based on the degree of association between the historical business demand information and the first business demand information of the current customer service session to be processed. The complexity of processing the business of the first object reflects the complexity of processing the current business of the first object, and the level of complexity will have a certain impact on the determination of the business processing priority of the first object.

[0045] Specifically, in this exemplary embodiment, the degree of association between the first business requirement information and the second business requirement information of the first object, such as the correlation correl, can be determined by the formula: Among them, Cov(y 3m ,z 1n ) is the variable y 3m and z 1n The covariance of 3m ) and D(z 1n ) is the variable y 3m and z 1n The variance of y 3m Indicates the historical business demand information of the first object in the historical customer service session, that is, the second business demand information, z 1n It represents the first business demand information of the first object in the current customer service session, m represents the processing capability of the second business demand information in the historical customer service session, such as the ability to resolve the historical intention, and n represents the processing capability of the first business demand information in the current customer service session. m and n can be selected from the pre-configured 1-5 levels. Different levels correspond to the percentage degree of the processing capability of business demand information in the customer service session. The processing capability of business demand information can represent whether the customer will express the same business demand information again when establishing a customer service session again. If the customer will not express the same business demand information again, it means that the processing capability of business demand information is high. If the customer will express the same business demand information again, it means that the business demand information was not properly processed last time, and the processing capability of business demand information is low. The complexity of processing the business of the first object can be determined by the following formula:

[0046] In addition, this exemplary embodiment takes into account that as the number of interactions in the customer service session increases, the customer's emotions will gradually change, and the long interaction time and the large number of interactions may result in the risk of not being able to provide accurate services to the customer, resulting in a poor customer experience, that is, emotional information will also affect the customer's business processing priority. Therefore, in this exemplary embodiment, when the first business demand information includes voice information, such as voice data spoken by the user, this exemplary embodiment can extract the voice features of the first object from the voice information, process the voice features, and obtain the emotional information of the first object, which is represented as z2. Among them, the voice features may include intonation change features, tone features, speech speed features, voiceprint features, etc., and the emotional risk generated by the first object when expressing the first business demand information can be mined or predicted through the voice features. The emotional risk can be characterized by emotional information. For example, when the first object establishes customer service sessions many times, it has a higher demand and urgency for solving its intentions. When expressing its intentions, the speed of speech is accelerated and the tone is aggravated, and the possibility of generating risks is greater. For example, when the questions raised are not reasonably solved many times, there may be a risk of customers initiating complaints. This exemplary embodiment can obtain emotional information by extracting speech features of the first object from the speech information and processing the speech features based on a pre-trained emotion recognition model or rule model. For example, the emotional features of the first object, such as voice pitch changes and speech speed changes, are input into the emotion recognition model for processing, and the emotional information of the first object is output. The value of the emotional information can be [0,100]. The higher the score, the higher the risk.

[0047] Finally, the business processing priority of the first object can be determined based on the complexity and emotional information, for example, by calculating the intention complexity data * the intention emotional risk data, and determining the business processing priority of the first object based on the calculation result.

[0048] In an exemplary embodiment, the attribute information includes service attribute information and behavior attribute information, and the first service requirement information includes voice information; Figure 3 As shown, the determining of the service processing priority of the first object based on the first service requirement information and the attribute information may include:

[0049] Step S310, determining the complexity of processing the business of the first object based on the degree of association between the first business requirement information and the second requirement information of the first object;

[0050] Step S320, extracting speech features from the speech information, and determining emotion information of the first object based on the speech features;

[0051] Step S330, determining a first evaluation value of the service for processing the first object based on the service attribute information; and determining a second evaluation value of the service for processing the first object based on the behavior attribute information;

[0052] Step S340, determining the business processing priority of the first object based on the complexity, the emotional information, the first evaluation value and the second evaluation value.

[0053] Among them, business attribute information refers to attribute information related to a specific business. For example, in financial scenarios such as repayment and lending, the business attribute information of the first object may be financial attribute information, such as account status, lending status, financial status, etc.; in communication scenarios such as calls and the Internet, the business attribute information may be communication attribute information, such as virtual account status, communication traffic status, etc. Behavior attribute information refers to attribute information of interactive behaviors related to the first object. For example, before the current customer service session, the first object entered an application related to the business and performed interactive operations such as browsing, clicking, and querying, or the first object made or received a call related to the business before the current customer service session. When the customer initiates a customer service session later, its purpose will be clearer. This exemplary embodiment can consider the business attribute information and behavior attribute information of the first object to obtain the first evaluation value and the second evaluation value. Further, the business processing priority of the first object can be determined according to the complexity, emotional information, the first evaluation value, and the second evaluation value.

[0054] In an exemplary embodiment, the business attribute information includes business type information of the first object, business service status of the first object, and business account status of the first object; and determining the first evaluation value of processing the business of the first object based on the business attribute information may include:

[0055] The second business evaluation value is determined according to the business type information of the first object, the business service status of the first object, and the business account status of the first object to determine the first evaluation value.

[0056] Among them, the business type information may refer to the type information of the service provided to the first object, which is represented as X1, and specifically includes the name, attributes, quantity of different types of service products under the name of the first object, whether there are partner products, etc. In the financial business scenario, different types of service products have different business complexity and risk levels. This exemplary embodiment can determine the business type assessment value from the perspective of the business type based on the business type information. The business type assessment value refers to data that evaluates the complexity and risk of the service from the dimension of the business type, and may include a first business complexity assessment value and a first business risk assessment value, wherein the first business complexity assessment value can be calculated by the formula: a1X1, and the first business risk assessment value can be calculated by the formula: Calculated. Among them, a1 is the complexity assessment coefficient, and b1 is the risk assessment coefficient. a1 can reflect the degree of influence of the solution capabilities of different service product business types. Considering that different platforms have different solution capabilities for service products, a1 can be used to measure the platform's solution capabilities for a variety of service products and assign values ​​according to actual needs. The same is true for b1.

[0057] The business service status refers to the ability status to handle the business of the first object, which is expressed as X2. The business service status varies depending on the service scenario. For example, in a financial scenario, the business service status of the first object can be the lending status of the first object, such as whether there is multi-party lending. In a financial scenario, lending behavior can reflect the degree of cross-redundancy of the customer's capital chain, the degree of capital tension, and the debt repayment ability status. If there is a problem with the capital flow of the first object, the funds in the platform will also be negatively affected with a high probability, and the stability will be poor. Therefore, the business service status evaluation value can be determined by the business service status, and the business service status evaluation value can include a second business risk evaluation value, wherein the second business risk evaluation value can be obtained through Calculated.

[0058] The business account status refers to the account status of the first object when it is currently being served, which is represented by X3. It can be related to a specific business type. For example, in a financial scenario, the business account status can be the financial account status of the first object, such as whether there is an overdue situation. When the account of the first object is in an overdue state, it means that there may be a problem with the customer's funds. If there is a service status of repeated collection, it may cause the customer to be in a poor emotional state and have more urgent demands; at the same time, it is related to the scalability needs generated by the overdue status, such as negotiated repayment, which involves more complex links such as trial calculations and prepayments, and a longer processing cycle, and the resulting service risks will also increase. In order to better estimate risks, overdue situations can be graded according to their overdue duration and the proportion of overdue products. Taking the above factors into consideration, this exemplary embodiment can evaluate the business account status from the dimension of business account status. The business account status evaluation value can include a third business complexity evaluation value and a third business risk evaluation value, where the third business complexity evaluation value can be obtained through the formula: The third business risk assessment value can be obtained through the formula: It should be noted that in X 3i When i is in the range of [1,5], it indicates the account status under different overdue periods, and when i is in the range of [6,8], it indicates the account status under different overdue proportions. a2 is the complexity assessment coefficient under the business account status dimension.

[0059] Further, the first evaluation value is determined based on the business type information of the first object, the business service status of the first object, and the business account status of the first object. The first evaluation value can be determined based on the business type evaluation value, the business service status evaluation value, and the business account status evaluation value. For example, the first evaluation value is determined by a cumulative calculation method, or a preset calculation formula.

[0060] In an exemplary embodiment, the behavior attribute includes a first behavior attribute of a first behavior and a second behavior attribute of a second behavior, the first behavior includes a behavior actively initiated by the first object, and the second behavior includes a behavior passively accepted by the first object;

[0061] Determining a second evaluation value of a business of processing the first object based on the behavior attribute information includes:

[0062] Based on the first behavior attribute, determining a third evaluation value of the business of processing the first object; and the second behavior attribute, determining a fourth evaluation value of the business of processing the first object;

[0063] Based on the third evaluation value and the fourth evaluation value, a second evaluation value is determined.

[0064] Among them, the first behavior and the second behavior are both the preceding behaviors before the time when the first object participates in the current session. The occurrence time of the first behavior can be before the occurrence time of the second behavior, or after the occurrence time of the second behavior, as long as it is the behavior before the current session. The first behavior includes the behavior actively initiated by the first object, and the first behavior attribute is the behavior attribute information generated by the first behavior, such as the information generated when the first object clicks, browses, collects, likes, communicates with the intelligent assistant, etc. in the application, such as browsing or clicking on the bill details page; the second behavior includes the behavior passively accepted by the first object, and the second behavior attribute is the behavior attribute information generated by the second behavior, such as the first object receives a business-related call, voice, text message, etc. dialed by the customer service, such as receiving a telemarketing text message, collection call, etc. from the platform. This exemplary embodiment can determine the third evaluation value and the fourth evaluation value respectively from the first behavior attribute and the second behavior attribute, and determine the second evaluation value based on the third evaluation value and the fourth evaluation value.

[0065] Among them, the third evaluation value may include the first behavior complexity evaluation value and the first behavior risk evaluation value. For example, before conducting a customer service conversation, the first object enters the application and performs interactive operations with a specific page, such as browsing and querying a bill page. Then the intention and demand of the current customer service conversation will be very clear. If the best service solution cannot be provided to them in a timely and rapid manner, their emotions will intensify relatively quickly, and there will be a higher service risk. In addition, if a customer service conversation is initiated after using the functions and services provided by the application, it means that the service product is temporarily unable to solve the customer's problem, which means that the complexity is higher. In this exemplary embodiment, in order to better predict risks, the types of pages browsed and the length of time the pages stay on can be graded, which can be done through y 1i Characterize the complexity or duration of different browsing pages, and based on y 1i Calculate the first behavior complexity assessment value and the first behavior risk assessment value. When i represents the complexity, for example, the value range is [1,3], which means the complexity of pages 1-3. When i represents the page dwell time, for example, the value range is [4,6], which means the dwell time of pages 1-3. Correspondingly, the first behavior complexity assessment value can be calculated by the formula: The first behavior risk assessment value can be calculated by the formula It should be noted that 1-6 here are only exemplary. In actual applications, the number of pages may include multiple. Depending on the number of pages, the indicator data of the dwell time on each page may also be included. Then, according to the complexity or dwell time of different pages, the first behavior complexity assessment value and the first behavior risk assessment value may be calculated. a3 is the complexity assessment coefficient under the dimension of pre-active behavior information.

[0066] The fourth behavior assessment value may include the second behavior risk assessment value. The pre-passive behavior information such as platform contact that customers passively receive before the customer service conversation can also be used as the reason for their demand. High-frequency behavior may cause customers to have resistance, which in turn causes customers to have emotions and complaint risks. At the same time, considering the time factor, the second behavior risk assessment value can be obtained by: Calculated. Wherein, a4 is the complexity evaluation coefficient under the second behavior, that is, the complexity evaluation coefficient under the dimension of the pre-passive behavior information. In this exemplary embodiment, a1, a2, a3, and a4 can be normalized for processing.

[0067] like Figure 4 , shows a flow chart of determining the service processing priority of a first object in this exemplary embodiment, which may specifically include the following steps:

[0068] Step S402, obtaining first information of a first object; the first information includes first business requirement information of the first object and attribute information of the first object;

[0069] Step S404, extracting first business requirement information of the first object from the first information;

[0070] Step S406, determining the complexity of the business of the first object according to the correlation between the business requirement information and the second business requirement information of the first object;

[0071] Step S408, when the first service demand information is voice information, extracting voice features from the first service demand information, and determining the emotion information of the first object according to the voice features;

[0072] Step S410, extracting business attribute information from the first information, and determining a first evaluation value of a business for processing the first object based on the business attribute information;

[0073] Step S412, extracting behavior attribute information from the first information, and determining a second evaluation value of the business of processing the first object based on the behavior attribute information;

[0074] Step S414, determining the business processing priority of the first object based on the complexity, the emotional information, the first evaluation value and the second evaluation value.

[0075] This exemplary embodiment can determine the service processing priority U of the first object according to the complexity, the emotion information, the first evaluation value and the second evaluation value. p , considering that there are differentiated weight distributions between different dimensions, weight t can be distributed for different data or specific evaluation values ​​used to constitute each dimension. Specifically, the formula can be used: Calculate the service processing priority of the first object, where: and z2 are based on the complexity of the business of the first object and the emotional information of the first object, is a first evaluation value determined according to the business attributes, is the second evaluation value determined according to the behavior attribute, and t1~t8 are weight coefficients.

[0076] Step S140 : determining a target service processing resource from a plurality of service processing resources based on the remaining resource amount of each service processing resource and the service processing priority.

[0077] Step S150: Allocate the service of the first object to the target service processing resource.

[0078] Among them, the target business processing resource refers to the business processing resource determined to be ultimately used to provide services or solve problems for the first object. This exemplary embodiment can determine the target business processing resource from the business processing resources based on the remaining resource amount and business processing priority of each business processing resource. For example, it can be determined whether the ranking of the business processing priority of the first object is within the remaining resource amount of the business processing resource. The more remaining resources, the greater the current service volume that can be borne. The remaining resource amount can be determined based on the maximum number of services carried by the business processing resource, or the current maximum parallel processing of services by the business processing resource. Then, the business processing resource whose business processing priority meets the remaining resource amount condition can be determined as the target business processing resource. Further, the business of the first object is allocated to the target business processing resource, so that the target business processing resource provides business services or solves problems for the first object, that is, the target business processing resource processes the business of the first object.

[0079] In an exemplary embodiment, determining a target service processing resource from a plurality of service processing resources based on the remaining resource amount and the service processing priority of each service processing resource includes:

[0080] Determine resource priorities for multiple business processing resources;

[0081] According to the resource priority order of the business processing resources, based on the remaining resource amount and the business processing priority of each business processing resource, determining in sequence whether the first object is successfully matched with each business processing resource;

[0082] According to the matching result, the business processing resource matching the first object is used as the target business processing resource.

[0083] When determining the target business processing resource from multiple business processing resources, this exemplary embodiment can match the first object in sequence according to the priority of the business processing resources. The priority of the business processing resources can reflect whether the business processing resources can better meet the service status of the target demand. For example, when a customer initiates a loan intention, the priority of the dedicated manual business processing resources is greater than the priority of the general manual business processing resources, and greater than the priority of the non-manual business processing resources. At this time, the first object can be determined in sequence according to the order of the dedicated manual business processing resources, the general manual business processing resources, and the non-manual business processing resources to determine whether the first object matches each candidate business processing resource to determine the target business processing resource.

[0084] In this exemplary embodiment, the business processing resources may include dedicated business processing resources, different dedicated business processing resources may solve different business demand information, different first business demand information may correspond to different dedicated business processing resources, and the business processing resources may also include other business processing resources, such as general business processing resources for solving general problems, intelligent business processing resources or non-manual business processing resources, etc. Dedicated business processing resources may be used to process the business of the first object with a higher priority, a higher importance or a higher complexity, etc. In this exemplary embodiment, it may be determined whether the first object matches the corresponding dedicated business processing resource based on the remaining resource amount and the business processing priority of the dedicated business processing resource corresponding to the first business demand information. If the match is successful, the dedicated business processing resource corresponding to the first business demand information may be used as the target business processing resource. If the match fails, the target business processing resource may be determined from other business processing resources other than the dedicated business processing resource corresponding to the first business demand information. The matching process may be a process of determining whether the business processing resource can process the business of the first object.

[0085] This exemplary embodiment may adopt a step-by-step matching approach to determine a target business processing resource among multiple business processing resources. When the business processing priority of a first object does not match a dedicated business processing resource, and it is necessary to determine the target business processing resource from other candidate business processing resources outside a dedicated manual available channel, it may be determined whether the business processing priority of the first object matches a general business processing resource. If the match is successful, the general business processing resource may be used as the target business processing resource. If the match fails, a non-manual business processing resource may be used as the target business processing resource. The manual business processing resource may be an intelligent business processing resource, such as using a pre-trained question-answering model as a processing model for a manual business processing resource.

[0086] In an exemplary embodiment, the above step S140, determining the target service processing resource from the service processing resources based on the remaining resource amount of each service processing resource and the service processing priority, may include:

[0087] Predict multiple sequence numbers according to the business processing priority; the multiple sequence numbers correspond one-to-one to the business processing resources, and the sequence number is the sorting sequence number of the business of the first object in the business processing resource;

[0088] The target business processing resource is determined according to multiple sequence numbers; the remaining resource amount of the target business processing resource is greater than or equal to the sequence number corresponding to the business of the first object in the target business processing resource.

[0089] The remaining resource amount of the business processing resource can reflect the number of businesses that the business processing resource can currently process, such as the maximum number of businesses that can be processed. In this exemplary embodiment, based on the remaining resource amount of each business processing resource and the business processing priority, the target business processing resource is determined from the business processing resources. First, multiple sequence numbers can be predicted based on the business processing priority. The sequence number can be the sorting sequence number of the business of the first object processed in the business processing resource. The multiple sequence numbers correspond to the business processing resources one by one. For example, in different business processing resources, the first object can correspond to a sorting sequence number based on its business processing priority. Then, the target business processing resource can be determined based on the multiple sequence numbers. If the remaining resource amount of the target business processing resource is greater than or equal to the sequence number corresponding to the target business processing resource, it means that the business processing resource corresponding to the first business demand information can process the business of the first object, and it can be determined as the target business processing resource.

[0090] It should be noted that, in this exemplary embodiment, the business processing priority of the first object may be ranked differently in different business processing resources. For example, after calculating the service score of the first object, the same score may be ranked differently in different business processing resources.

[0091] In addition, in this exemplary embodiment, considering that the dedicated business processing resources corresponding to the first business demand information may include multiple ones, after determining to allocate the first object to the dedicated business processing resource, this exemplary embodiment can also specifically determine to which dedicated business processing resource the business of the first object is allocated. For example, when including dedicated business processing resources a and b that can process loan business, these dedicated business processing resources can be sorted, for example, according to the current idle processing volume, processing efficiency, processing speed and other factors, and then matched in turn in multiple dedicated business processing resource lists according to the business processing priority of the first object, and the first object is allocated to the successfully matched dedicated business processing resource for business processing. For example, if the dedicated business processing resource list of the first object is arranged as a and b according to the priority, the business processing priority of the first object can be used to enter the dedicated business processing resource a for queuing. If the dedicated business processing resource a cannot be provided, it can enter the dedicated business processing resource b for queuing, etc.

[0092] Based on the above description, in this exemplary embodiment, first information is obtained; the first information includes first business demand information of the first object and attribute information of the first object; multiple business processing resources are determined based on the first business demand information; based on the first business demand information and / or attribute information, the business processing priority of the first object is determined; based on the remaining resource amount and the business processing priority of each business processing resource, a target business processing resource is determined from multiple business processing resources; and the business of the first object is allocated to the target business processing resource. On the one hand, this exemplary embodiment proposes a new data processing method. Compared with the prior art method of allocating business by acquiring historical information, this exemplary embodiment can fully mine the first information related to the first object, convert the mined first information into the business processing priority of the first object, and determine the target business processing resources of the first object based on the business processing priority. It can accurately determine the target business processing resources for processing the business of the first object, and quickly allocate the business of the first object, which greatly improves the data processing efficiency and effectiveness; on the other hand, this exemplary embodiment can obtain the business processing priority for the first object according to the business demand information and / or attribute information of the first object, and can realize the accurate capture and evaluation of the personalized needs of different first objects, and provide different first objects with a variety of data processing methods based on the business processing priority; on the other hand, this exemplary embodiment can quickly determine the target business processing resource that meets the current business processing priority from multiple business processing resources based on the business processing priority, greatly shorten the waiting time of the first object, and can effectively improve the data processing experience.

[0093] In an exemplary embodiment, obtaining the first information includes: obtaining session information in which the first object participates, and parsing the session information to obtain the first information, wherein the session information includes session information of a current round.

[0094] In actual applications, the first object may raise multiple rounds of business demand information in the customer service conversation. For example, after the customer expresses for the first time, if the information is diverted to non-manual business processing resources, there may be three situations. First, the user is satisfied with the solution provided by the non-manual business processing resources, but this has generated other new intentions, so the user will actively output the new intention through voice or keystrokes; second, the user has doubts about the services provided by non-manual business processing resources and expresses the demand to enter dedicated business processing resources for services. Questions can be recommended based on the user's behavioral attribute information, business attribute information, etc. to guide the user to express specific intentions; third, the user has not actively expressed, and the system can ask the user to confirm "whether the problem has been solved" and "whether there are other questions, please describe the specific problems", etc., and then after the user expresses again, the second round of calculation and matching process will be entered.

[0095] Therefore, there may be a situation where the first object proposes multiple rounds of business demand information. In this exemplary embodiment, obtaining the first information may include obtaining session information in which the first object participates, and parsing the session information to obtain the first information, wherein the session information may include session information of the current round, or may include session information of all rounds, and the first business demand information, the business processing priority of the first object and other information may be updated according to the session information of different rounds, so as to determine the target processing resources for processing the business of the first object in different rounds.

[0096] In this exemplary embodiment, after the first object is allocated to the target business processing resource in the first round, the first information of the next session round can be parsed according to the session information of the first object in the next session round, and the first information can include the first business requirement information of the next session round and the attribute information of the first object. For example, assuming that the business requirement information of the first session round is A intention, it can be regarded as the current session round is A intention. In the case where the business of the first object is processed by the target business processing resource, the session information of the second round is parsed to obtain the first business requirement information of the second round, such as B intention, and then the business processing priority of the first object is updated according to the B intention of the next session round, and the target business processing resource of the second session round is re-determined, and the first object is allocated to the re-determined target business processing resource. Wherein, updating the business processing priority of the first object can be to accumulate the evaluation values ​​of the first information of multiple session rounds, or to calculate it according to the evaluation values ​​of the first information in different session rounds and the weights of different session rounds.

[0097] In this exemplary embodiment, the session information of different rounds may change, and the corresponding first information may also be different. For example, the first business demand information of the first object in the first session round is the repayment intention, while the first business demand information of the second session round is the loan intention. Similarly, the attribute information of the first object may also change, such as the financial-related business attribute information, or the behavior attribute information may also change, and then the complexity of the business of the first object, the emotional information of the first object, the first evaluation value, and the second evaluation value of the first object may change. Therefore, it is necessary to update the business processing priority of the first object according to the complexity of the business of the first object in the next session round, the emotional information of the first object, the first evaluation value, and the second evaluation value.

[0098] In an exemplary embodiment, the increment of the service processing priority calculated according to the first information after the next round of update can be added to the service processing priority of the previous session round to determine the service processing priority of the first object in the next session round. For example, when calculating the service processing priority of the second session round, the service processing priority of the first object can be first determined according to the first information after the second session round of update, and the service processing priority is used as an increment. The service processing priority in the second session round is calculated according to the service processing priority increment and the service processing priority of the first object obtained in the first session round, for example, the service processing priority increment is added to the service processing priority of the first object obtained in the first session round to obtain the service processing priority in the second session round. In this exemplary embodiment, the service processing priority of multiple session rounds can be determined by: the total service processing priority of the first object = the service processing priority in the first session round + the service processing priority in the second session round + ... + the service processing priority in the nth session round.

[0099] In an exemplary embodiment, in the next session round, the session information may update the target business demand information of the first object. For example, the second session round expresses multiple first business demand information again, and it is different from the first business demand information of the first session round. In this case, the target business demand information needs to be updated, and the corresponding business processing resources and the remaining resource amount of each business processing resource, such as the number of processable businesses, are redetermined according to the target business demand information, and then the target business processing resources are determined again from the redetermined business processing resources.

[0100] In this exemplary embodiment, if the allocation result is to enter non-manual business processing resources, the first object can actively express its intention, or recommend possible business demand information to the first object based on the first object's behavior attribute information, business attribute information, etc., and perform a new round of processing and determine the target business processing resources based on the new business demand information. That is, every time the first object expresses the first business demand information, it is necessary to calculate the business processing priority once and perform real-time dynamic sorting. When a single customer service session involves multiple session rounds, the total quantitative business processing priority of a single customer service session to be served is the sum of multiple rounds, which can be expressed as: Where p represents the round.

[0101] The above embodiment is used as an example below to illustrate that the attribute information of the first object in the first information of the first object includes: business attribute information that the account status is that the customer is overdue, behavior attribute information that the bill page has been browsed before the call, and collection calls have been received, and historical business demand information that the repayment method has been consulted before this call. In this customer service conversation, in the first conversation round, the first business demand information of the first object is to inquire about the repayment date, the voice feature reflects that the emotional information of the first object is at a normal level, and the business type information is repayment related. At this time, the business processing priority sorting number based on the above first object is 100, and the remaining resource amount of the dedicated business processing resources is 50. The match is unsuccessful, and it enters the general business processing resources for re-sorting. After the updated sorting, it is at 50, and the remaining resource amount of the general business processing resources is 30. The match is unsuccessful. Therefore, the output result after the first round of interaction is a non-human customer service business processing resource. In the second conversation round, the customer service representative expresses the intention to negotiate installment repayment, and the emotional characteristic is angry. After recalculating the business processing priority, the output ranking result is 20, and the remaining resources of the dedicated customer service business processing resources are 30. Then the service is successfully entered into the specific group of manual business processing resources for service processing.

[0102] Figure 5 A schematic diagram of a service processing flow in this exemplary embodiment is shown, taking two rounds of conversation as an example, which may specifically include:

[0103] Step S502, obtaining first information of a first object in a first conversation round; the first information includes first business requirement information of the first object in the first conversation round and attribute information of the first object;

[0104] Step S504, determining a plurality of service processing resources for a first session round according to the first service demand information;

[0105] Step S506, determining a service processing priority of the first object in the first conversation round based on the first service requirement information and / or attribute information;

[0106] Step S508, predicting multiple sequence numbers according to the service processing priority; the multiple sequence numbers correspond to the sequence numbers of the service processing priority in different service processing resources;

[0107] Step S510, determining whether the remaining amount of the dedicated service processing resources corresponding to the first service demand information is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resources;

[0108] If the remaining amount of the dedicated service processing resource corresponding to the first service demand information is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resource, executing step S512, determining the dedicated service processing resource as the target service processing resource, and allocating the service of the first object to the dedicated service processing resource;

[0109] If the remaining amount of the dedicated service processing resources corresponding to the first service demand information is less than the sequence number of the service processing priority in the dedicated service processing resources, executing step S514 to determine whether the remaining amount of the general service processing resources is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resources;

[0110] If the remaining amount of the general business processing resource is greater than or equal to the sequence number of the business processing priority in the dedicated business processing resource, step S516 is executed to determine the general business processing resource as the target business processing resource and allocate the business of the first object to the general business processing resource;

[0111] If the remaining amount of the general business processing resource is less than the sequence number of the business processing priority in the dedicated business processing resource, executing step S518, determining the non-manual business processing resource as the target business processing resource, and allocating the first object to the non-manual business processing resource;

[0112] If new first business requirement information is generated, step S520, obtaining first information of the first object in the second conversation round; the first information includes the first business requirement information of the first object in the second conversation round and attribute information of the first object;

[0113] Step S522, updating multiple service processing resources according to the first service demand information of the second session round;

[0114] Step S524, determining a service processing priority increment of the first object according to the first service requirement information and / or attribute information of the second conversation round, and adding the increment to the service processing priority of the first object obtained in the second conversation round to obtain the service processing priority of the first object in the second conversation round;

[0115] Step S526, in the second conversation round, predicting multiple sequence numbers according to the service processing priority;

[0116] Step S528, determining whether the remaining amount of the dedicated service processing resources corresponding to the first service demand information is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resources;

[0117] If the remaining amount of the dedicated service processing resource corresponding to the first service demand information is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resource, executing step S530, determining the dedicated service processing resource as the target service processing resource, and allocating the service of the first object to the dedicated service processing resource;

[0118] If the remaining amount of the dedicated service processing resources corresponding to the first service demand information is less than the sequence number of the service processing priority in the dedicated service processing resources, executing step S532 to determine whether the remaining amount of the general service processing resources is greater than or equal to the sequence number of the service processing priority in the dedicated service processing resources;

[0119] If the remaining amount of the general business processing resource is greater than or equal to the sequence number of the business processing priority in the dedicated business processing resource, step S534 is executed to determine the general business processing resource as the target business processing resource and allocate the business of the first object to the general business processing resource;

[0120] If the remaining amount of the general business processing resource is less than the sequence number of the business processing priority in the dedicated business processing resource, step S536 is executed to determine the non-manual business processing resource as the target business processing resource and allocate the first object to the non-manual business processing resource.

[0121] The exemplary embodiment of the present disclosure also provides a service processing device. Figure 6 The device 600 may include a first information acquisition module 610 for acquiring first information; the first information includes first business demand information of the first object and attribute information of the first object; a processing resource determination module 620 for determining multiple business processing resources based on the first business demand information; a priority determination module 630 for determining the business processing priority of the first object based on the first business demand information and / or attribute information; a target resource determination module 640 for determining a target business processing resource from multiple business processing resources based on the remaining resource amount and business processing priority of each business processing resource; and a first object allocation module 650 for allocating the business of the first object to the target business processing resource.

[0122] In an exemplary embodiment, the target resource determination module 640 includes: a sequence number prediction unit, which is used to predict multiple sequence numbers according to the business processing priority; the multiple sequence numbers correspond one-to-one to the business processing resources, and the sequence number is the sorting sequence number of the business of the first object processed in the business processing resources; the target resource determination unit is used to determine the target business processing resource according to the multiple sequence numbers; the remaining resource amount of the target business processing resource is greater than or equal to the sequence number corresponding to the business of the first object in the target business processing resource.

[0123] In an exemplary embodiment, the first service requirement information includes voice information, and the priority determination module 630 includes: a complexity determination unit for determining the complexity of processing the service of the first object based on the degree of association between the first service requirement information and the second requirement information of the first object;

[0124] The emotional information determination unit is used to extract voice features from the voice information and determine the emotional information of the first object based on the voice features; the priority determination unit is used to determine the business processing priority of the first object based on the complexity and the emotional information.

[0125] In an exemplary embodiment, the attribute information includes business attribute information and behavior attribute information, and the first business demand information includes voice information; the priority determination module 630 includes: a complexity determination unit, which is used to determine the complexity of processing the business of the first object based on the degree of association between the first business demand information and the second demand information of the first object; an emotional information determination unit extracts voice features from the voice information, and determines the emotional information of the first object based on the voice features; an evaluation value determination unit, which is used to determine a first evaluation value for processing the business of the first object based on the business attribute information; and determines a second evaluation value for processing the business of the first object based on the behavior attribute information; a priority determination unit, which is used to determine the business processing priority of the first object based on the complexity, emotional information, the first evaluation value and the second evaluation value.

[0126] In an exemplary embodiment, the behavior attributes include a first behavior attribute of a first behavior and a second behavior attribute of a second behavior, the first behavior includes behavior actively initiated by the first object, and the second behavior includes behavior passively accepted by the first object; the evaluation value determination unit includes: an evaluation value determination first subunit, used to determine a third evaluation value of processing the business of the first object based on the first behavior attribute; and a second behavior attribute, used to determine a fourth evaluation value of processing the business of the first object; an evaluation value determination second subunit, used to determine a second evaluation value based on the third evaluation value and the fourth evaluation value.

[0127] In an exemplary embodiment, obtaining the first information includes: obtaining session information in which the first object participates, and parsing the session information to obtain the first information, wherein the session information includes session information of a current round.

[0128] In an exemplary embodiment, there are multiple first business demand information, the multiple first business demand information include third business demand information and at least one fourth business demand information, and the generation time of the third business demand information is later than the generation time of the fourth business demand information; the processing resource determination module 620 includes: a business processing resource determination unit, which is used to determine multiple business processing resources according to the third business demand information.

[0129] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0130] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0131] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above data processing method is implemented.

[0132] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0133] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0134] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0135] Computer programs can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. Electronic devices can convert signals carrying computer programs into digital signals to run computer programs. When a computer program runs on an electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned data processing method, which includes the following steps: obtaining first information; the first information includes first business demand information of a first object and attribute information of the first object; determining multiple business processing resources based on the first business demand information; determining the business processing priority of the first object based on the first business demand information and / or the attribute information; determining a target business processing resource from the multiple business processing resources based on the remaining resource amount of each of the business processing resources and the business processing priority; allocating the business of the first object to the target business processing resource.

[0136] The exemplary embodiment of the present disclosure also provides an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as program code. The processor executes the method in the exemplary embodiment by executing the executable instructions. In addition, the electronic device may also include a display for displaying a graphical user interface.

[0137] Reference below Figure 7 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Figure 7 The electronic device 700 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0138] like Figure 7 As shown, the electronic device 700 may include: a processor 710 , a memory 720 , a bus 730 , an I / O (input / output) interface 740 , a network adapter 750 , and a display 760 .

[0139] The memory 720 may include a volatile memory, such as a RAM 721, a cache unit 722, and may also include a non-volatile memory, such as a ROM 723. The memory 720 may also include one or more program modules 724, such program modules 724 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 724 may include each module in the above-mentioned device.

[0140] The processor 710 may include one or more processing units. For example, the processor 710 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0141] The processor 710 may be used to execute executable instructions stored in the memory 720, such as executing the above-mentioned data processing method.

[0142] The bus 730 is used to realize the connection between different components of the electronic device 700, and may include a data bus, an address bus, and a control bus.

[0143] The electronic device 700 can communicate with one or more external devices 800 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 740 .

[0144] The electronic device 700 can communicate with one or more networks through the network adapter 750. For example, the network adapter 750 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 750 can communicate with other modules of the electronic device 700 through the bus 730.

[0145] The electronic device 700 can display a graphical user interface through the display 760, such as displaying a game editing scene.

[0146] although Figure 7 Not shown, other hardware and / or software modules may also be provided in the electronic device 700, including but not limited to: a display (if it has been mentioned above that the electronic device includes a display, then the word "display" shall be deleted here), microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0147] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0148] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

[0149] It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as a system, method or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which may be collectively referred to herein as a "circuit", "module" or "system". Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and implementation are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0150] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A data processing method, characterized in that: include: Obtaining first information; The first information includes first business requirement information of the first object and attribute information of the first object; Determine a plurality of business processing resources based on the first business demand information; Determining a service processing priority of the first object based on the first service requirement information and / or the attribute information; Determining a target business processing resource from the multiple business processing resources based on the remaining resource amount of each of the business processing resources and the business processing priority; Allocate the service of the first object to the target service processing resource.

2. The method according to claim 1, characterized in that The determining the target business processing resource from the business processing resources based on the remaining resource amount of each of the business processing resources and the business processing priority includes: Predicting multiple sequence numbers according to the business processing priority; the multiple sequence numbers correspond one-to-one to the business processing resources, and the sequence numbers are the order numbers of the business of the first object in the business processing resources; The target business processing resource is determined according to the multiple sequence numbers; the remaining resource amount of the target business processing resource is greater than or equal to the sequence number corresponding to the business of the first object in the target business processing resource.

3. The method according to claim 1, characterized in that The first service requirement information includes voice information, and determining the service processing priority of the first object based on the first service requirement information includes: Determining the complexity of processing the business of the first object based on the degree of association between the first business requirement information and the second requirement information of the first object; Extracting speech features from the speech information, and determining emotion information of the first object based on the speech features; Based on the complexity and the emotion information, a business processing priority of the first object is determined.

4. The method according to claim 1, characterized in that: The attribute information includes service attribute information and behavior attribute information, and the first service requirement information includes voice information; and determining the service processing priority of the first object based on the first service requirement information and the attribute information includes: Determining the complexity of processing the business of the first object based on the degree of association between the first business requirement information and the second requirement information of the first object; Extracting speech features from the speech information, and determining emotion information of the first object based on the speech features; Determine a first evaluation value for processing the business of the first object based on the business attribute information; and determine a second evaluation value for processing the business of the first object based on the behavior attribute information; Based on the complexity, the emotional information, the first evaluation value, and the second evaluation value, a business processing priority of the first object is determined.

5. The method according to claim 4, characterized in that The behavior attributes include a first behavior attribute of a first behavior and a second behavior attribute of a second behavior, the first behavior includes a behavior actively initiated by the first object, and the second behavior includes a behavior passively accepted by the first object; The determining, based on the behavior attribute information, a second evaluation value of the business of processing the first object includes: Based on the first behavior attribute, determining a third evaluation value for processing the service of the first object; and based on the second behavior attribute, determining a fourth evaluation value for processing the service of the first object; Based on the third evaluation value and the fourth evaluation value, the second evaluation value is determined.

6. The method according to claim 1, characterized in that The acquiring of the first information includes: acquiring session information in which the first object participates, and parsing the session information to obtain the first information, wherein the session information includes session information of a current round.

7. The method according to claim 1, characterized in that There are multiple first business demand information, the multiple first business demand information include third business demand information and at least one fourth business demand information, and the generation time of the third business demand information is later than the generation time of the fourth business demand information; The determining a plurality of business processing resources based on the first business requirement information includes: A plurality of business processing resources are determined according to the third business demand information.

8. A data processing device, characterized in that: include: A first information acquisition module, used to acquire first information; The first information includes first business requirement information of the first object and attribute information of the first object; A processing resource determination module, configured to determine a plurality of service processing resources based on the first service demand information; a priority determination module, configured to determine a service processing priority of the first object based on the first service requirement information and / or the attribute information; a target resource determination module, configured to determine a target business processing resource from the plurality of business processing resources based on the remaining resource amount of each of the business processing resources and the business processing priority; The first object allocation module is used to allocate the business of the first object to the target business processing resource.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

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

Images