Processing device, processing method, and program

Abstract

To provide a processing device, a processing method, and a program capable of deriving a more appropriate solution.SOLUTION: A processing device 2 includes: a neural network 210 as a first processing unit that constructs a scenario composed of a plurality of response stages and at least one or more pieces of first information used for a response in each response stage by performing machine learning of past responses; and an AI chatbot 100 as a second processing unit responding with a solution according to the scenario and a third processing unit responding with another solution by tracing through the response stages in the opposite direction from a state in which the solution has already been fixed until the solution is reached.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a processing device, a processing method, and a program. [Background technology]

[0002] There are chatbots (automatic conversation programs using text) that use artificial intelligence (AI) (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 186678 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is no chat or chatback (chat version of callback) that uses already accumulated data to solve a problem by working backward from a state where the solution has already been determined, based on a solution obtained from a neural network or a multi-layer neural network (deep neural network) that uses deep learning. Hereinafter, "solving a problem by working backward from a state where the solution has already been determined" will be referred to as "solving using backward methods."

[0005] The present invention has been made in view of the above-mentioned problems, and provides a processing device, a processing method, and a program that can derive a more appropriate solution. [Means for solving the problem]

[0006] In order to solve the above problems, the processing device according to the present invention includes a first processing unit that constructs a scenario consisting of a plurality of response steps and at least one or more first pieces of information used for a response in each response step by machine learning past responses, a second processing unit that responds with a solution in accordance with the scenario, and a third processing unit that responds with another solution by tracing back the response steps from a state in which a solution has already been determined until the solution is reached. The third processing unit is characterized in that it changes the scenario by linking two pieces of first information at different response stages and responds with another solution according to the changed scenario. In addition, the processing device of the present invention comprises a first processing unit that constructs a scenario consisting of multiple response steps and at least one or more first pieces of information to be used for responding at each response step by machine learning past responses, a second processing unit that responds with a solution according to the scenario, and a third processing unit that responds with another solution by tracing back the response steps from a state where a solution has already been determined to the state where the solution is reached, and is characterized in that when it determines that a solution cannot be achieved using the scenario, the third processing unit responds with a solution different from the solution derived by the scenario.

[0007] Furthermore, a processing method according to the present invention is a processing method in a processing device, the processing device having a first step of constructing a scenario consisting of a plurality of response steps and at least one or more first pieces of information used for the response in each response step by machine learning past responses, a second step of responding with a solution in accordance with the scenario, and a third step of responding with another solution by tracing back the response steps from a state in which a solution has already been determined to the solution in question. In the third step, the scenario is changed by linking the two pieces of first information at different response stages, and another solution is responded in accordance with the changed scenario. Furthermore, the processing method of the present invention is a processing method in a processing device, wherein the processing device has a first step of constructing a scenario consisting of a plurality of response stages and at least one or more first pieces of information to be used for the response at each response stage by machine learning past responses, a second step of responding with a solution according to the scenario, and a third step of responding with another solution by tracing back the response stages from a state where a solution has already been determined to the solution reached, wherein in the third step, if it is determined that a solution cannot be achieved using the scenario, the processing device responds with a solution different from the solution derived by the scenario.

[0008] The program according to the present invention causes a computer to function as a first processing unit that constructs a scenario consisting of a plurality of response steps and at least one or more first pieces of information used for the response at each response step by machine learning past responses, a second processing unit that responds with a solution in accordance with the scenario, and a third processing unit that responds with another solution by tracing back the response steps from a state where a solution has already been determined to the solution in question. The third processing unit is characterized in that it changes the scenario by linking two pieces of first information at different response stages and responds with another solution according to the changed scenario. In addition, the program of the present invention causes a computer to function as a first processing unit that constructs a scenario consisting of multiple response steps and at least one or more first pieces of information to be used for responding at each response step by machine learning past responses, a second processing unit that responds with a solution in accordance with the scenario, and a third processing unit that responds with another solution by tracing back the response steps from a state in which a solution has already been determined to the solution reached, and is characterized in that the third processing unit responds with a solution different from the solution derived by the scenario when it determines that a solution cannot be achieved using the scenario. [Effects of the Invention]

[0009] According to the present invention, a more appropriate solution can be derived. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic configuration diagram of a processing apparatus according to an embodiment of the present invention; [Figure 2]FIG. 1 is an image diagram of a scenario used in a processing device according to an embodiment of the present invention. [Figure 3] 4 is an example of a data configuration of customer information stored in a processing device according to an embodiment of the present invention. [Figure 4] 4 is a diagram illustrating an example of a data configuration of response history information stored in a processing device according to an embodiment of the present invention. [Figure 5] This diagram shows the flow (1) of a scenario (guidance) using a "reverse solution" constructed using a neural network (deep neural network). [Figure 6] This diagram shows the flow (2) of a scenario (guidance) using a "reverse solution" constructed using a neural network (deep neural network). [Figure 7] This diagram shows the flow (3) of a scenario (guidance) using a "reverse solution" constructed using a neural network (deep neural network). DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Each figure is merely a schematic illustration to the extent that the present invention can be fully understood. Therefore, the present invention is not limited to only the illustrated examples. Furthermore, in this embodiment, explanations of configurations that are not directly related to the present invention or well-known configurations may be omitted. In addition, in each figure, common or similar components are assigned the same reference numerals, and redundant explanations thereof will be omitted.

[0012] <Configuration of response system including processing device according to embodiment> A response system 1 including a processing device 2 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a schematic configuration diagram of a response system 1 including a processing device 2 according to an embodiment.

[0013] The response system 1 shown in FIG. 1 is a system that responds to inquiries from customers. The response system 1 is, for example, a contact center system, and the following description will be given assuming a response task of responding to inquiries about financial products. Note that the application field of the response system 1 is not particularly limited. As will be described in detail later, the response system 1 not only responds to customer inquiries in real time, but also allows the response system 1 to later provide chatback (a chat version of callback) from the response system 1. Responses by the response system 1 include both chat responses (e.g., see reference numeral 135 in FIG. 1) and telephone responses (e.g., see reference numeral 130 in FIG. 1). Note that the response system 1 also allows the response time to be specified according to the customer, and the operator to be specified according to the operator's availability.

[0014] The response system 1 includes a processing device 2. The processing device 2 is, for example, an application server, and is configured as a computer having a CPU (Central Processing Unit), memory, storage means (storage unit, storage device) such as a hard disk, and a network interface. This computer realizes various functions by the CPU executing programs loaded into the memory.

[0015] The processing device 2 mainly includes a processing unit 3 having an AI chatbot 100, a database 200, and a neural network 210. The database 200 stores response history information 220 and customer information 230. The neural network 210 is generated from the information stored in the database 200, for example. Note that the neural network 210 is an example of a "first processing unit," and examples of the "first processing unit" are not limited to the neural network 210. Furthermore, the AI ​​chatbot 100 is an example of a "second processing unit" and a "third processing unit," and examples of the "second processing unit" and the "third processing unit" are not limited to the AI ​​chatbot 100.

[0016] The AI ​​chatbot 100 has a function that responds to inquiries from customers via chat. The AI ​​chatbot 100 accepts inquiries via chat and responds based on a scenario derived by, for example, a neural network 210. The neural network 210 may be configured as a multi-layer neural network (deep neural network) using deep learning. The neural network 210 is constructed, for example, by machine learning past responses with customers. Note that a scenario is the flow (plot) of an automated voice response. A scenario is composed of, for example, multiple pieces of guidance. The guidance may be, for example, the content of an inquiry (question) made to a customer or a suggestion to a customer, but is not limited to this. The content of this guidance may differ depending on the situation.

[0017] 2 shows an image of a scenario (that is, a transition of guidance) used by the processing device 2. FIG. 2 is an image diagram of a scenario used by the processing device 2. The scenario shown in FIG. In Figure 2, squares with letters inside represent guidance, and the lines connecting the guidance indicate the transition of the guidance. The scenario shown in Figure 2 has a tree structure with branches based on the guidance and its response results. In other words, the scenario consists of multiple response stages and at least one guidance used in the response at each response stage. The scenario shown in Figure 2 approaches a final solution (answer or proposal) to the customer's inquiry as it progresses from left to right. In other words, guidances "E" to "L" are final solutions (answers or proposals) to the customer's inquiry, and guidances "A" to "J" are inquiries (questions) to obtain the final solution (answer or proposal). For example, the AI ​​chatbot 100 proceeds through the question of guidance "A," the question of guidance "B," and the question of guidance "C," and finally answers the customer with the proposal of guidance "E." Hereinafter, in the scenario shown in Figure 2, the left side of the page may be referred to as "upstream" and the right side of the page may be referred to as "downstream." The guidance that constitutes the scenario is an example of the "first information," and examples of the "first information" are not limited to the guidance.

[0018] In this embodiment, it is assumed that the AI ​​chatbot 100 or the operator 110 responds to a chat or phone call sent from the customer to the processing device 2 as a first response and conveys a solution (answer or suggestion). Then, as a second response, the processing device 2 sends a chat or phone call to the customer to convey a new solution (answer or suggestion) different from the solution from the first response. For example, as a first response, the AI ​​chatbot 100 makes inquiries and suggestions in the order of ("A" → "B" → "C" → "E"), and then makes inquiries and suggestions in the order of ("E" → "C" → "B" → "A" → "I" → "J" → "K"). In such a situation, for example, an "insurance contract" recommended to the general public would be answered with guidance "E," but considering the occupation, age, etc., it would be more appropriate to answer with guidance "K" to recommend the "insurance contract." In this embodiment, we focus on the processing during chatback (calls from the processing device 2 to the customer), and explain the first response sent from the customer to the processing device 2, assuming that it is completed in principle.

[0019] Next, the customer information 230 stored in the database 200 will be described with reference to Fig. 3. Fig. 3 shows an example of the data structure of the customer information 230 held by the processing device 2. 3 mainly includes, for example, a customer identification field 231, a customer category field 232, a gender field 233, an age field 234, a region field 235, and an occupation field 236. Note that the configuration shown here is an example, and other configurations may also be used. The customer identification column 231 stores information that can identify a customer. The customer classification column 232 stores information that classifies customers based on preset criteria. The customer classification column 232 may store composite information, and in FIG. 3, information such as "rank," anonymous / general / important, etc. is stored. The gender column 233 stores information about the gender of the customer. The age column 234 stores information about the customer's age. The area column 235 stores information about the area where the customer is located (the area where the customer's activities are based). The occupation column 236 stores information about the customer's occupation.

[0020] The customer information 230 shown in Fig. 3 is used to determine how to respond to a customer. That is, the processing device 2 manages customer information (for example, rank, anonymous / general / important, gender, age, occupation, etc.) in the customer information 230, and determines how the chat operator will respond based on this information. In this embodiment, the following response is determined based on the information in the customer category column 232, etc. Note that the response methods shown here are merely examples. Details of the response methods will be described later. Customer A decides to use only the chatbot. Customer B decides to use either a chatbot or an operator, or both. Customer C decides to use either a chatbot or an operator, or both. Customer D decides to use only the chatbot. ·Customer E decides to handle the call with "operator only."

[0021] Next, the response history information 220 stored in the database 200 will be described with reference to FIG. 4. FIG. 4 shows an example of the data configuration of the response history information 220 held by the processing device 2. The response history information 220 includes the response history between the operator (human) and the customer, and the response history between the AI ​​chatbot 100 and the customer. The response history between the operator (human) and the customer is mainly used as information for generating the neural network 210. On the other hand, the response history between the AI ​​chatbot 100 and the customer is used as basic information for processing during chatback (transmission from the processing device 2 to the customer). Note that FIG. 4 shows a case where customer C has requested chatback from an operator, customer E has requested chatback specifying a time and operator, and no other customers have made any particular requests.

[0022] 4 mainly includes, for example, a customer identification field 221, a reception time field 222, a response time field 223, a chatback information field 224, and a response content field 225. Note that the configuration shown here is an example, and other configurations may also be used. The customer identification column 221 stores information that can identify a customer. The reception time column 222 stores the time when the customer made an inquiry. The response time column 223 stores the time when a response was made to a customer (or the time when a response will be made). The chatback information field 224 stores information about chatback (e.g., the time of chatback, whether operator assistance is required, and the method of response). For example, customer C is an important customer, and has received a request for operator assistance, so the status is "operator assistance required." When the status is "operator assistance required," for example, the AI ​​chatbot 100 requests an operator to respond (see reference numeral 120 in FIG. 1). The response content column 225 stores the response content between the operator (human) or AI chatbot 100 and the customer.

[0023] The characteristic processing performed by the processing device 2 during chatback will be described with reference to FIGS. 5 to 7 (and also with reference to FIGS. 1 to 4 as appropriate). FIG. 5 is a diagram showing a scenario (guidance) flow (1) using a "backward solution" constructed using the neural network 210 (deep neural network). FIG. 6 is a diagram showing a scenario (guidance) flow (2) using a "backward solution" constructed using the neural network 210 (deep neural network). FIG. 7 is a diagram showing a scenario (guidance) flow (3) using a "backward solution" constructed using the neural network 210 (deep neural network). "Backward solution" here means "solving by working backward from a state where a solution has already been determined."

[0024] In this embodiment, when the AI ​​(processing unit 3) helps the operator solve the problem, the AI ​​solves the connection between the flow of the "content of the inquiry" from the "AI" to the "customer" at each of the following "A" to "L" (see Figure 5) and the scenario (guidance) by using already accumulated data and a solution obtained from a multi-layer neural network 210 (deep neural network) using a neural network or deep learning, by working backward from the state where the solution has already been determined (i.e., solving using a backward direction).

[0025] For example, in the state shown in Figure 5, if the content of the inquiry is already in the "E" state and can be resolved by taking it to "K," the AI ​​(processing unit 3) determines that it is best to guide it to the "K" state and guides it accordingly (see the bold and dotted arrows in Figure 5). In this case, the AI ​​chatbot 100 responds to the inquiry by saying that it is best to resolve it in the following order ("E" → "C" → "B" → "A" → "I" → "J" → "K"). In other words, it returns upstream once and then guides it downstream via another route, responding with a new solution.

[0026] Also, as shown in Figure 6, if the AI ​​(processing unit 3) determines that it is impossible to help the operator solve the problem using the existing flow, either the operator or the AI ​​(processing unit 3), or both, may link new guidance together to guide the operator to solve the problem (see the thick line connecting "C" in Figure 6 with "I," the response step one step upstream). In this case, the operator responds to the inquiry via the AI ​​chatbot 100, for example, that the best way to solve the problem is ("E" → "C" → "I" → "J" → "K"). Note that the example shown here is a case where "B" and "A" have already been determined to be unnecessary or impossible.

[0027] Also, as shown in FIG. 7, when the AI ​​(processing unit 3) determines that a new solution is necessary, either the operator or the AI ​​(processing unit 3), or both, may set a new solution (see "X" in FIG. 7). In this case, the operator replies to the inquiry, for example, via the AI ​​chatbot 100, that it would be best to resolve the issue using another method, "X." Note that the example shown here is a case where the scenario (guidance) flow constructed using the current neural network 210 (deep neural network) has already been determined to be unnecessary or unacceptable.

[0028] 1 to 7, examples of operations during chatback in the processing device 2 will be shown. Note that the examples of operations shown here are merely examples. Also, it is not necessary to perform all of the examples of operations shown here, and it is possible to select one or several of them and operate them, for example.

[0029] (Example 1) In the case of "Customer A" in the customer information 230 shown in Figure 3, if it has been decided that the customer should be handled "only by the chatbot" because the customer has a low "rank" and is anonymous, for example, the AI ​​chatbot 100 is made to respond according to the "flow of a scenario (guidance) constructed using the neural network 210 (deep neural network) (see Figure 2)." In this case, only the AI ​​chatbot 100 responds, and the operator does not respond according to the flow. Furthermore, guidance and responses using a solution using the reverse direction (see Figure 5) are not provided.

[0030] (Example 2) In the case of "Customer B" in the customer information 230 shown in Figure 3, where the "rank" and other information have been determined and it has been decided that the case will be handled by "one or both of the chatbot and the operator," for example, the AI ​​chatbot 100 and the operator will be made to respond in the order of "Flow (1) of the scenario (guidance) by "solution using backward direction" constructed using the neural network 210 (deep neural network) (see Figure 5)" → "Flow (2) of the scenario (guidance) by "solution using backward direction" constructed using the neural network 210 (deep neural network) (see Figure 6)."

[0031] For example, the problem is that the content of the inquiry is already in the "E" state, and the AI ​​(processing unit 3) determines that it is best to guide the inquiry to the "K" state. Considering the customer's "gender, age, region, and occupation," this is the case when the "gender, age, region, and occupation" are more in line with the "gender, age, region, and occupation" assumed in the content of the inquiry for "K" than the "gender, age, region, and occupation" assumed in the content of the inquiry for "E." In this case, for example, the AI ​​chatbot 100 may first provide guidance and answer using flow (1), then provide guidance and answer using flow (2), and if the problem still cannot be resolved, an operator may respond to the individual chat or phone call.

[0032] (Example 3) In the case of "Customer C" in the customer information 230 shown in Figure 3, where the "rank" and other information have been determined as an "important customer," and therefore it has been decided that the customer will be handled by "one or both of a chatbot and an operator," for example, the AI ​​chatbot 100 and the operator will be made to respond in the following order: "Flow (1) of scenario (guidance) by "solution using backward direction" constructed using the neural network 210 (deep neural network) (see Figure 5)" → "Flow (2) of scenario (guidance) by "solution using backward direction" constructed using the neural network 210 (deep neural network) (see Figure 6)" → "Flow (3) of scenario (guidance) by "solution using backward direction" constructed using the neural network 210 (deep neural network) (see Figure 7)."

[0033] For example, the problem is that the content of the inquiry is already in the "E" state, and the AI ​​(processing unit 3) determines that it is best to guide the inquiry to the "K" state. Considering the customer's "gender, age, region, and occupation," this is the case when the "gender, age, region, and occupation" are more in line with the "gender, age, region, and occupation" assumed in the content of the inquiry for "K" than the "gender, age, region, and occupation" assumed in the content of the inquiry for "E." In this case, for example, the AI ​​chatbot 100 may first provide guidance and answer using flow (1), then provide guidance and answer using flow (2), and then provide guidance and answer using flow (3), and if the problem still cannot be resolved, an operator may respond to the individual chat or phone call.

[0034] (Example 4) In the case of "Customer D" in the customer information 230 shown in Figure 3, where the "rank" and other information have been determined and it has been decided to handle the case "only with the chatbot," for example, the AI ​​chatbot 100 can be made to respond using "flow (1) (see Figure 5) of a scenario (guidance) using "solution using backward direction" constructed using the neural network 210 (deep neural network)."

[0035] For example, the problem is that the content of the inquiry is already in the "E" state, and the AI ​​(processing unit 3) determines that it is best to guide the inquiry to the "K" state. Considering the customer's "gender, age, region, and occupation," this is a case where the "gender, age, region, and occupation" partially match the "gender, age, region, and occupation" assumed in the inquiry content of "K" rather than the "gender, age, region, and occupation" assumed in the inquiry content of "E." In this case, for example, the AI ​​chatbot 100 may first provide guidance and a response according to flow (1), and if the problem is still not resolved, an operator may respond to the individual chat.

[0036] (Example 5) In the case of "Customer E" in the customer information 230 shown in Figure 3, when it has been decided that the designated "operator only" will handle the case because the response time and operator have been specified, for example, the operator will be made to handle the case using "flow (1) (see Figure 5) of a scenario (guidance) using "solution using backward direction" constructed using the neural network 210 (deep neural network)." In this case, for example, an operator may first provide guidance and answer according to flow (1), and if the problem is still not resolved, the operator may respond to the individual chat or phone call.

[0037] As described above, the processing device 2 according to the embodiment solves a problem by working backward from the state where the solution has already been determined, based on the solution obtained from the multilayer neural network 210 (deep neural network) using a neural network or deep learning (i.e., solving using a backward approach). For example, in the state shown in FIG. 5, if the problem is that the query content is already in state "E" and can be solved by moving to "K," the processing device 2 determines that it is best to guide the query to state "K" and guides the query (see the bold and dotted arrows in FIG. 5). Therefore, the processing device 2 can derive a more appropriate solution.

[0038] Furthermore, the processing device 2 according to the embodiment changes its operation based on the customer information 230 shown in Fig. 3. This makes it possible to derive a more appropriate solution tailored to the customer.

[0039] [Variations] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be practiced within the scope of the claims. [Explanation of symbols]

[0040] 1. Response System 2 Processing equipment 3 Processing section 100 AI Chatbots 110 Operator 200 databases 210 Neural Networks 220 Response History Information 230 Customer information

Claims

1. A first processing unit that constructs a scenario including a plurality of response stages and at least one or more pieces of first information used for a response in each response stage by machine learning of past responses; A second processing unit that responds with a solution according to the scenario; a third processing unit that responds with another solution by tracing the response steps from a state in which a solution has already been determined to a state in which the solution has been reached in a backward direction; Equipped with The third processing unit changes the scenario by combining two pieces of the first information in different response stages, and responds with another solution according to the changed scenario. A processing device comprising:

2. A first processing unit that constructs a scenario including a plurality of response stages and at least one or more pieces of first information used for a response in each response stage by machine learning of past responses; A second processing unit that responds with a solution according to the scenario; a third processing unit that responds with another solution by tracing the response steps from a state in which a solution has already been determined to a state in which the solution has been reached in a backward direction; Equipped with when it is determined that the problem cannot be solved by the scenario, the third processing unit responds with a solution different from the solution derived by the scenario. A processing device comprising:

3. The first processing unit constructs the scenario using a neural network.

3. The processing device according to claim 1 or 2.

4. A processing method in a processing device, comprising: The processing device includes: A first step of constructing a scenario including a plurality of response stages and at least one or more first pieces of information used for the response in each response stage by machine learning of past responses; A second step of responding with a solution according to said scenario. A third step of responding with another solution by tracing backward the response steps from an already determined solution to the solution in question; having In the third step, the scenario is changed by combining the two pieces of first information at different response stages, and another solution is responded according to the changed scenario. A processing method comprising:

5. A processing method in a processing device, comprising: The processing device includes: A first step of constructing a scenario including a plurality of response stages and at least one or more first pieces of information used for the response in each response stage by machine learning of past responses; A second step of responding with a solution according to said scenario. A third step of responding with another solution by tracing backward the response steps from an already determined solution to the solution in question; having In the third step, if it is determined that the problem cannot be solved by the scenario, a response is made with a solution different from the solution derived by the scenario. A processing method comprising:

6. Computer, a first processing unit that constructs a scenario including a plurality of response stages and at least one or more pieces of first information used for a response in each response stage by machine learning of past responses; a second processing unit that responds with a solution according to the scenario; a third processing unit that responds with another solution by tracing back through the response steps from a state in which a solution has already been determined to the solution in question; Function as a The third processing unit changes the scenario by combining two pieces of the first information in different response stages, and responds with another solution according to the changed scenario. A program characterized by:

7. Computer, a first processing unit that constructs a scenario including a plurality of response stages and at least one or more pieces of first information used for a response in each response stage by machine learning of past responses; a second processing unit that responds with a solution according to the scenario; a third processing unit that responds with another solution by tracing back through the response steps from a state in which a solution has already been determined to the solution in question; Function as a When the third processing unit determines that the problem cannot be solved by the scenario, the third processing unit responds with a solution different from the solution derived by the scenario. A program characterized by:

Images